© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6778
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    KommentareTeilen
    -0.57
    InteropServices
    -0.57
    has
    -0.52
     has
    -0.51
     Has
    -0.48
    立
    -0.46
     recenti
    -0.46
    Has
    -0.44
    viser
    -0.43
    HAS
    -0.43
    POSITIVE LOGITS
     }}$}
    0.66
     didst
    0.62
     Connectez
    0.61
     Suivez
    0.60
    EDEFAULT
    0.59
     invokingState
    0.59
     Efq
    0.57
     calendriers
    0.57
     było
    0.56
     estekak
    0.56
    Activations Density 2.279%

    No Known Activations