© 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. 16333
    Prev
    Next
    INDEX
    Explanations

    technical documents about flow, charts, or spinal cords

    oai_token-act-pair · gemini-2.0-flash

    flow

    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
    ضور
    -0.53
    platt
    -0.52
    Break
    -0.51
    ctos
    -0.48
    InitStruct
    -0.47
    unchecked
    -0.47
    })`
    -0.47
    manjaro
    -0.47
     inimes
    -0.46
    ')['
    -0.46
    POSITIVE LOGITS
    \{\\
    0.73
    UnusedPrivate
    0.60
    styleType
    0.60
     initComponents
    0.58
     surla
    0.57
     برانيه
    0.57
    chastic
    0.57
    IBOutlet
    0.55
    !*\
    0.55
     Huguen
    0.52
    Activations Density 2.386%

    No Known Activations