© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13614
    Prev
    Next
    INDEX
    Explanations

    words associated with searching/seeking something or expressing opinions/preferences.

    oai_token-act-pair · gemini-2.0-flash

    class or method names in programming

    np_token-act-pair-logits · gpt-4o-mini

    variable assignments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    '
    -0.53
    ↵↵
    -0.52
    <bos>
    -0.51
    <eos>
    -0.45
     pre
    -0.43
    وزی
    -0.42
    ↵
    -0.42
     second
    -0.40
    r
    -0.40
    sed
    -0.39
    POSITIVE LOGITS
    ArgsConstructor
    1.02
    MigrationBuilder
    0.99
    UserScript
    0.94
    AndEndTag
    0.93
    Personensuche
    0.93
    MemoryWarning
    0.89
    #+#
    0.88
    Diwedd
    0.87
     feroit
    0.86
    IsMutable
    0.85
    Activations Density 5.939%

    No Known Activations