© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3888
    Prev
    Next
    INDEX
    Explanations

    words used to describe story plots, character development, and social issues in television and film.

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MLLoader
    -0.85
     getItemId
    -0.60
    esez
    -0.56
    ModelSerializer
    -0.54
     jScrollPane
    -0.53
    awtextra
    -0.52
    ContentAlignment
    -0.52
    setViewportView
    -0.52
    Portale
    -0.52
     समीक्षाओं
    -0.51
    POSITIVE LOGITS
     Beatty
    0.60
     Lola
    0.59
     stratégique
    0.57
     Diallo
    0.57
     Suzy
    0.57
     Lydia
    0.56
     Nadia
    0.56
     Jace
    0.56
    GEBURTS
    0.55
     Ophelia
    0.55
    Activations Density 28.678%

    No Known Activations