© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11379
    Prev
    Next
    INDEX
    Explanations

    the prefix "bi" often followed by a hyphen

    oai_token-act-pair · gemini-2.0-flash

    'bi' prefixes in various languages

    np_token-act-pair-logits · gpt-4o-mini

    bi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AnchorStyles
    -0.57
     unknownFields
    -0.51
    XmlEnum
    -0.51
    Crossref
    -0.47
     segre
    -0.47
    AutoSize
    -0.46
     initWithFrame
    -0.43
    AdapterView
    -0.41
    createForm
    -0.41
    Autriche
    -0.40
    POSITIVE LOGITS
    saraba
    0.73
     autorytatywna
    0.72
     مرئيه
    0.65
    WebElementEntity
    0.65
     Савезне
    0.63
    nmgp
    0.61
    Rhestr
    0.60
    ngdoc
    0.58
    ientôt
    0.57
    सन्दर्भ
    0.57
    Activations Density 0.305%

    No Known Activations