© 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. 815
    Prev
    Next
    INDEX
    Explanations

    statistics and numbers

    oai_token-act-pair · gemini-2.0-flash

    Report snippets

    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
     ModelExpression
    -0.41
     autant
    -0.40
     Kebijakan
    -0.39
    аб
    -0.38
    AxisAlignment
    -0.37
    Range
    -0.37
    IntoConstraints
    -0.37
    -------------</
    -0.36
     pprint
    -0.36
     غير
    -0.36
    POSITIVE LOGITS
    +:+
    0.84
    offsetof
    0.62
     ExecuteAsync
    0.62
    onAttach
    0.61
    DTD
    0.60
    IContainer
    0.59
    migrationBuilder
    0.57
     ſta
    0.57
    queryInterface
    0.57
    +#+
    0.56
    Activations Density 12.304%

    No Known Activations