© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11790
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, names, possessive pronouns, and words related to journalism or conflict.

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     <=",
    -0.52
    וויק
    -0.48
     DRAWINGS
    -0.46
    ederos
    -0.44
    rower
    -0.43
    Phew
    -0.43
    uttavia
    -0.42
    Наде
    -0.42
    nall
    -0.41
    Ҭ
    -0.41
    POSITIVE LOGITS
    XmlAccessType
    0.63
     виправивши
    0.61
    Hochspringen
    0.57
    دانشنامهٔ
    0.57
    didSet
    0.56
    Portály
    0.56
     &___
    0.55
    yntaxException
    0.55
    VolleyError
    0.52
     CanadaChoose
    0.52
    Activations Density 0.901%

    No Known Activations