© 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. 8608
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and monetary quantities

    oai_token-act-pair · gemini-2.0-flash

    dashes

    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
     circonstances
    -0.57
    válasz
    -0.56
    lauch
    -0.56
    mű
    -0.56
    ckså
    -0.56
    pagation
    -0.55
    parency
    -0.55
     necesito
    -0.53
    komendasi
    -0.52
     romantique
    -0.52
    POSITIVE LOGITS
    less
    0.72
    elemField
    0.55
    LESS
    0.54
    VIAF
    0.51
    hpp
    0.51
    as
    0.49
    hyrchwyd
    0.48
    more
    0.47
    XmlAccessType
    0.47
     محفوظة
    0.46
    Activations Density 13.128%

    No Known Activations