© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12217
    Prev
    Next
    INDEX
    Explanations

    mentions of movies and filming

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    -2.63
    film
    -2.30
     Film
    -2.28
    Film
    -2.25
     FILM
    -2.08
     films
    -2.03
    FILM
    -1.75
     Films
    -1.73
    films
    -1.73
    Films
    -1.68
    POSITIVE LOGITS
    tagHelperRunner
    0.89
     EconPapers
    0.81
    ंदीखरीदारी
    0.75
    izzera
    0.67
    Przypisy
    0.66
    ⓧ
    0.66
    IntoConstraints
    0.64
    hyrchwyd
    0.63
     незавершена
    0.62
    URLException
    0.60
    Activations Density 0.524%

    No Known Activations