© 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. 3968
    Prev
    Next
    INDEX
    Explanations

    words related to the process of reading or writing

    oai_token-act-pair · gemini-2.0-flash

    code/foreign text

    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
     read
    -2.83
    read
    -2.39
     Read
    -2.30
    Read
    -2.27
     READ
    -1.91
     reads
    -1.70
    READ
    -1.63
     Reads
    -1.45
     listen
    -1.34
    reads
    -1.30
    POSITIVE LOGITS
    GraphicsUnit
    0.65
    GEBURTSDATUM
    0.60
    tagHelperRunner
    0.60
    الدراسه
    0.58
    Einzelnachweise
    0.57
     ویکی‌پدیای
    0.56
    unknownFields
    0.53
    İstinadlar
    0.52
    stateProvider
    0.52
    contentLoaded
    0.52
    Activations Density 12.180%

    No Known Activations