© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to context analysis and specific actions

    oai_token-act-pair · gemini-2.0-flash

    technical/legal documents

    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
    mustang
    -0.48
    MethodManager
    -0.46
    ichia
    -0.46
    lgari
    -0.46
    riors
    -0.46
    eriks
    -0.44
    ARDI
    -0.44
     godine
    -0.44
    utives
    -0.44
    urtles
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.75
    Παραπομπές
    0.69
    ngdoc
    0.61
     ImGui
    0.60
    AccessorTable
    0.59
    Rohy
    0.59
     مرئيه
    0.58
    homonymie
    0.57
     Pristupljeno
    0.57
    ")));
    0.56
    Activations Density 1.660%

    No Known Activations