© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3986
    Prev
    Next
    INDEX
    Explanations

    words relating to advice based on the context and tone.

    oai_token-act-pair · gemini-2.0-flash

    action words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     scon
    -0.43
    fxml
    -0.43
    хіво
    -0.42
    OwnProperty
    -0.41
    দ্
    -0.39
    avras
    -0.39
     Reverso
    -0.37
    dellín
    -0.37
    Tembelea
    -0.36
    фраструк
    -0.36
    POSITIVE LOGITS
     action
    1.59
     Action
    1.45
    Action
    1.39
     ACTION
    1.39
    action
    1.38
    ACTION
    1.28
     Actions
    1.27
     actions
    1.27
     acción
    1.20
    Actions
    1.18
    Activations Density 2.356%

    No Known Activations