© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8740
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of people and organizations

    oai_token-act-pair · gemini-2.0-flash

    technical terms and concepts

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

    interpersonal relationships

    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
     dets
    -0.55
     dubbio
    -0.50
     vieilles
    -0.48
     lourdes
    -0.48
     merito
    -0.44
     связано
    -0.43
     couverts
    -0.42
     vieille
    -0.42
    ypress
    -0.42
     closely
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    0.87
    ArrowToggle
    0.84
    ImageContext
    0.80
    GEBURTSDATUM
    0.79
    URLException
    0.76
    RegressionTest
    0.75
    extAlignment
    0.73
     насељу
    0.73
     فريبيس
    0.72
    principalTable
    0.72
    Activations Density 3.841%

    No Known Activations