© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    names of organizations or institutions

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming-related terms

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

    academic institutions

    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
    allin
    -0.55
     @"/
    -0.53
     friv
    -0.52
    loth
    -0.51
    queryInterface
    -0.49
     officiel
    -0.48
    ниципа
    -0.48
    ?')
    -0.47
    sinki
    -0.46
     않았
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.77
    migrationBuilder
    0.73
    ніципалі
    0.69
    MessageOf
    0.67
     المعيارى
    0.65
     intptr
    0.65
    bootstrapcdn
    0.64
     NSCoder
    0.63
    astify
    0.61
    SBATCH
    0.61
    Activations Density 10.713%

    No Known Activations