© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11789
    Prev
    Next
    INDEX
    Explanations

    questions

    oai_token-act-pair · gemini-2.0-flash

    question and answer pairs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCulture
    -0.84
    tvguidetime
    -0.73
    fromnode
    -0.70
    rungsseite
    -0.65
     فريبيس
    -0.60
    fxml
    -0.56
     vectorielles
    -0.54
    AndEndTag
    -0.53
    onAttach
    -0.53
     CreateTagHelper
    -0.50
    POSITIVE LOGITS
     the
    0.98
     your
    0.69
    limus
    0.52
     seu
    0.52
     their
    0.52
    esteld
    0.50
     some
    0.50
    MemoryWarning
    0.48
    rodow
    0.47
    among
    0.46
    Activations Density 0.745%

    No Known Activations