© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    language describing the features and operation of a karaoke microphone

    oai_token-act-pair · 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
    SPATH
    -0.57
    ColumnHeaders
    -0.56
     Roskov
    -0.51
    homonymie
    -0.49
     JpaRepository
    -0.49
     poveznice
    -0.48
    erals
    -0.48
    zeciw
    -0.47
     SSC
    -0.47
    positories
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.58
    новништво
    0.54
     Audiodateien
    0.54
    tainty
    0.50
    makeText
    0.50
     generous
    0.50
    rté
    0.50
    зопас
    0.49
     teis
    0.49
     deciso
    0.49
    Activations Density 7.838%

    No Known Activations