© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12594
    Prev
    Next
    INDEX
    Explanations

    words that denote possession, especially using "his", "'s", and "herself", some pronouns like "she" and related terms, plus a few adjectives like "final", "surviving", and "various"

    oai_token-act-pair · gemini-2.0-flash

    Characters and their relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.71
    évaluateur
    -0.68
    ThroughAttribute
    -0.67
    ########.
    -0.65
     ویکی‌پدی
    -0.62
    principalColumn
    -0.60
     المعيارى
    -0.60
    @[+][
    -0.60
    IUrlHelper
    -0.59
    ViewFeatures
    -0.59
    POSITIVE LOGITS
     master
    0.50
     grace
    0.49
    brid
    0.49
    FailureListener
    0.48
     Sem
    0.47
    CrossRef
    0.47
     regenerative
    0.46
     mano
    0.46
     handler
    0.45
     Grace
    0.45
    Activations Density 1.492%

    No Known Activations