© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14314
    Prev
    Next
    INDEX
    Explanations

    the word "recovery".

    oai_token-act-pair · gemini-2.0-flash

    recovery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    pertino
    -0.76
    @[+][
    -0.69
     bes
    -0.69
     Paglinawan
    -0.66
    makeText
    -0.66
    antMatchers
    -0.65
    holde
    -0.63
    enegro
    -0.62
     Deserialize
    -0.62
    agna
    -0.61
    POSITIVE LOGITS
    ReusableCell
    0.79
    tagHelperRunner
    0.73
    σθαι
    0.71
     pettico
    0.64
    ſelf
    0.62
     orgas
    0.61
     handker
    0.60
     Phry
    0.60
     Vergine
    0.59
     OCS
    0.58
    Activations Density 1.205%

    No Known Activations