© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8343
    Prev
    Next
    INDEX
    Explanations

    official statements or quotes from officials

    oai_token-act-pair · gemini-2.0-flash

    statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     CURIAM
    -0.53
    曖昧さ回避
    -0.52
    ecore
    -0.46
    __).
    -0.46
    нительно
    -0.45
    Ƚ
    -0.44
    Ễ
    -0.44
    нал
    -0.44
    lardır
    -0.43
     fyr
    -0.43
    POSITIVE LOGITS
     statement
    1.92
     Statement
    1.62
    statement
    1.60
     statements
    1.56
    Statement
    1.50
     STATEMENT
    1.48
     Statements
    1.46
    STATEMENT
    1.34
    statements
    1.28
     spokesperson
    1.27
    Activations Density 0.531%

    No Known Activations