© 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. 15523
    Prev
    Next
    INDEX
    Explanations

    completed actions and laws

    oai_token-act-pair · gemini-2.0-flash

    Past events

    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
     ModelExpression
    -0.65
     Vikipedi
    -0.54
     defaultstate
    -0.52
    SuspendLayout
    -0.49
    ्रो
    -0.48
     stay
    -0.48
    providedIn
    -0.47
    Stay
    -0.47
     poursuite
    -0.46
     whilst
    -0.46
    POSITIVE LOGITS
    twice
    0.66
    SharedModule
    0.60
     twice
    0.59
    InputBorder
    0.58
    Twice
    0.56
     Twice
    0.56
     skak
    0.54
    celain
    0.53
     zweimal
    0.53
     mehrfach
    0.52
    Activations Density 3.540%

    No Known Activations