© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12907
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and symbols associated with legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    crime and trials

    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
    addPreferredGap
    -0.72
     ModelExpression
    -0.72
     transfieras
    -0.70
     дописавши
    -0.69
     <=",
    -0.68
     EconPapers
    -0.66
    IVEREF
    -0.65
     useStyles
    -0.64
     AssemblyCulture
    -0.64
    AndEndTag
    -0.64
    POSITIVE LOGITS
     publicitaires
    0.48
     nargin
    0.47
     hó
    0.47
     فريبيس
    0.46
     onOptions
    0.45
    nocześnie
    0.45
     spoilers
    0.44
    acb
    0.44
    icitis
    0.44
     diamantes
    0.44
    Activations Density 6.516%

    No Known Activations