© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7001
    Prev
    Next
    INDEX
    Explanations

    references to city blocks, streets, and the act of walking

    oai_token-act-pair · gemini-2.0-flash

    block/blocks

    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
     >=",
    -0.76
    SourceChecksum
    -0.71
    ArrowToggle
    -0.68
     autorytatywna
    -0.66
    complexContent
    -0.66
    LookAnd
    -0.66
     Numerade
    -0.63
    bootstrapcdn
    -0.59
    rrggbb
    -0.57
     незавершена
    -0.56
    POSITIVE LOGITS
     block
    1.46
     blocks
    1.40
    block
    1.21
     BLOCK
    1.16
     Blocks
    1.16
     Block
    1.15
    blocks
    1.14
    Block
    1.06
    BLOCK
    1.03
    Blocks
    1.02
    Activations Density 1.529%

    No Known Activations