© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1245
    Prev
    Next
    INDEX
    Explanations

    stack traces

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    )_/¯
    -0.68
    ⓧ
    -0.63
    Datuak
    -0.60
    InSection
    -0.59
    ReusableCell
    -0.57
    ohistochemistry
    -0.56
     tempore
    -0.56
    Hozzáférés
    -0.56
     harmonies
    -0.55
     Atenas
    -0.54
    POSITIVE LOGITS
    EndContext
    0.47
     rö
    0.46
     Bei
    0.46
     ***!
    0.46
    Ans
    0.44
    jeb
    0.43
    itse
    0.42
    芹
    0.42
     chale
    0.42
     المعيارى
    0.42
    Activations Density 1.946%

    No Known Activations