© 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. 5409
    Prev
    Next
    INDEX
    Explanations

    documentation about the Slack API and its various tokens

    oai_token-act-pair · gemini-2.0-flash

    Software and team collaboration

    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
     opérateur
    -0.56
     operator
    -0.56
     Operator
    -0.52
     operador
    -0.49
     Operators
    -0.48
    operator
    -0.47
    Operator
    -0.47
    untung
    -0.47
     opérateurs
    -0.47
     operators
    -0.46
    POSITIVE LOGITS
    WithIOException
    0.75
     teams
    0.72
     team
    0.70
     initComponents
    0.65
     Efq
    0.64
    team
    0.61
     équipe
    0.61
     Paglinawan
    0.60
    parsedMessage
    0.60
    TEAM
    0.60
    Activations Density 1.918%

    No Known Activations