© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1938
    Prev
    Next
    INDEX
    Explanations

    text referring to three-dimensional imaging or analysis

    oai_token-act-pair · gemini-2.0-flash

    say "dimensional"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     dimension
    -2.36
     Dimension
    -2.22
    Dimension
    -2.09
    dimension
    -2.05
     dimensions
    -1.98
     DIMENSION
    -1.98
     Dimensions
    -1.89
     dimensional
    -1.88
     Dimensional
    -1.83
    dimensions
    -1.77
    POSITIVE LOGITS
    AndEndTag
    0.55
    oprot
    0.52
     Guthrie
    0.49
    bitat
    0.49
    GetHashCode
    0.45
    CompilerServices
    0.45
    bindValue
    0.44
    Reparto
    0.44
     Blockly
    0.42
    docx
    0.42
    Activations Density 2.086%

    No Known Activations