© 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. 12675
    Prev
    Next
    INDEX
    Explanations

    words related to cinematography and film festivals

    oai_token-act-pair · gemini-2.0-flash

    film

    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
     film
    -1.82
    film
    -1.63
     films
    -1.63
     movie
    -1.62
     Film
    -1.62
    Film
    -1.59
    movie
    -1.52
     FILM
    -1.52
     filme
    -1.48
    FILM
    -1.45
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     transfieras
    0.54
     demografica
    0.50
    RegistryLite
    0.49
     &___
    0.48
     '{@
    0.48
    Šaltiniai
    0.46
     ISNI
    0.45
    +:+
    0.45
     sound
    0.43
    Activations Density 1.703%

    No Known Activations