© 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. 14637
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating some degree of certainty or truthfulness, as well as negativity or critical viewpoints regarding a previously made statement.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     مشين
    -0.66
    (!__
    -0.61
    İstinadlar
    -0.59
    `,
    -0.59
    Written
    -0.55
    protoimpl
    -0.55
     Written
    -0.55
    "},
    -0.54
    ScopeManager
    -0.54
     للاسماء
    -0.53
    POSITIVE LOGITS
    cienza
    0.56
    GEBURTSDATUM
    0.52
    بوابة
    0.52
    wning
    0.52
    cheme
    0.50
    antidad
    0.50
    ingale
    0.50
    izr
    0.48
    godic
    0.48
    vermögen
    0.47
    Activations Density 12.994%

    No Known Activations