© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10920
    Prev
    Next
    INDEX
    Explanations

    a jumble of things related to scientific and technical data, as well as Japanese language

    oai_token-act-pair · gemini-2.0-flash

    Scientific extracts/components

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.93
    parsedMessage
    -0.92
     MainAxisSize
    -0.92
    ^(@)
    -0.91
     Jefus
    -0.90
     newBuilder
    -0.88
     betweenstory
    -0.88
     AssemblyCulture
    -0.87
     Monfieur
    -0.86
     Majefty
    -0.85
    POSITIVE LOGITS
    -
    0.45
    _
    0.45
    ?
    0.42
    ing
    0.40
    .
    0.39
    list
    0.38
    '
    0.37
    !
    0.37
    f
    0.37
    c
    0.37
    Activations Density 0.848%

    No Known Activations