© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11810
    Prev
    Next
    INDEX
    Explanations

    words that appear in film review snippets related to emotion, tone, or direction in film

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     continúas
    -0.82
    rawDesc
    -0.80
    NameInMap
    -0.78
     nahilalakip
    -0.74
    ########.
    -0.73
    scriptcase
    -0.71
     Emits
    -0.70
    CloseOperation
    -0.69
     Preferencias
    -0.68
    <?
    -0.67
    POSITIVE LOGITS
     élevées
    0.56
     étranger
    0.55
     sociaux
    0.53
     fermés
    0.49
     mentales
    0.49
     militaires
    0.48
     invités
    0.48
     religieuses
    0.47
     élevés
    0.47
     giudi
    0.46
    Activations Density 2.685%

    No Known Activations