© 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. 12391
    Prev
    Next
    INDEX
    Explanations

    words related to politics, honor, or officialdom

    oai_token-act-pair · gemini-2.0-flash

    interactions

    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
     betweenstory
    -0.75
     Wikimedijinoj
    -0.74
    piac
    -0.59
    abestanden
    -0.58
    audiovisuel
    -0.54
     الحره
    -0.54
    ֹת
    -0.54
     мәкалә
    -0.54
    الحياه
    -0.53
    ulary
    -0.52
    POSITIVE LOGITS
    MigrationBuilder
    0.53
    gonic
    0.46
     CWE
    0.43
     aio
    0.41
    waitKey
    0.41
    策
    0.41
     ejected
    0.40
    ;
    0.40
    seguro
    0.39
    cente
    0.39
    Activations Density 2.463%

    No Known Activations