© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206517
    Prev
    Next
    INDEX
    Explanations

    looking to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.29
    د
    0.28
    ت
    0.27
    т
    0.26
    ب
    0.24
    require
    0.23
    िवर्स
    0.23
     be
    0.23
     Бүгенге
    0.23
    "
    0.23
    POSITIVE LOGITS
    ية
    0.22
     algéb
    0.21
    ákat
    0.21
    ).
    0.21
    ánchez
    0.21
    able
    0.20
    க்கான
    0.20
     campaigner
    0.19
    -
    0.19
    ’
    0.19
    Activations Density 0.004%

    No Known Activations