© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14701
    Prev
    Next
    INDEX
    Explanations

    statements of fact

    oai_token-act-pair · gemini-2.0-flash

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    XmlAccessType
    -0.64
     comuniques
    -0.63
    例文帳に追加
    -0.59
     is
    -0.53
     was
    -0.51
    ViewImports
    -0.51
    ERVIS
    -0.50
    OGND
    -0.50
    Hozzáférés
    -0.50
     nyelven
    -0.49
    POSITIVE LOGITS
     purpoſe
    0.82
     myſelf
    0.82
     ſtate
    0.76
     uſe
    0.73
     ſeveral
    0.72
     tranſ
    0.71
     Eſ
    0.70
     ſtand
    0.70
     eſ
    0.67
     neceſſ
    0.67
    Activations Density 4.129%

    No Known Activations