© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13256
    Prev
    Next
    INDEX
    Explanations

    references to media, including movies, television, media roles, awards, festivals, and people related to film

    oai_token-act-pair · gemini-2.0-flash

    film

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     film
    -1.05
     films
    -0.96
    film
    -0.94
     Film
    -0.86
    Film
    -0.85
     movies
    -0.82
     movie
    -0.80
     FILM
    -0.78
    FILM
    -0.76
    films
    -0.75
    POSITIVE LOGITS
    клопе
    0.77
    <bos>
    0.69
    AsUp
    0.65
    Kilder
    0.63
    脚注の使い方
    0.59
    دانشنامهٔ
    0.56
     ISNI
    0.56
    Билгалдахарш
    0.56
    Obrázky
    0.56
    apimachinery
    0.55
    Activations Density 2.458%

    No Known Activations