© 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. 16257
    Prev
    Next
    INDEX
    Explanations

    words related to the medium of film and film festivals

    oai_token-act-pair · gemini-2.0-flash

    film/movie

    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
     législation
    -0.50
    ดิน
    -0.50
    esség
    -0.45
     kell
    -0.44
    usercontent
    -0.43
     het
    -0.43
     geda
    -0.43
     créativité
    -0.42
    ell
    -0.41
    Vo
    -0.40
    POSITIVE LOGITS
    ArgsConstructor
    0.93
     CreateTagHelper
    0.80
     MainAxisSize
    0.77
    !*\
    0.75
     Waray
    0.74
    astify
    0.71
    $_['
    0.68
    Datuak
    0.68
    الدراسه
    0.67
    </thead>
    0.66
    Activations Density 2.591%

    No Known Activations