© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 358
    Prev
    Next
    INDEX
    Explanations

    legal and human rights investigations and claims

    oai_token-act-pair · gemini-2.0-flash

    official investigations

    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
    دانشنامهٔ
    -0.77
    UrlResolution
    -0.75
    WEBPACK
    -0.69
    MigrationBuilder
    -0.62
    ViewChild
    -0.62
    RTLD
    -0.62
    uxxxx
    -0.60
    DropTable
    -0.60
    UnusedPrivate
    -0.60
     سكانية
    -0.60
    POSITIVE LOGITS
     متعلقه
    0.58
    存于互联网档案馆
    0.47
    fia
    0.45
     Harbor
    0.45
    far
    0.44
    <![
    0.43
    fromnode
    0.43
     chắn
    0.43
    roli
    0.43
    ayaquil
    0.43
    Activations Density 12.426%

    No Known Activations