© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206005
    Prev
    Next
    INDEX
    Explanations

    numbers and specific entities

    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_20_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
     whiskey
    0.13
     శరీ
    0.12
     whisky
    0.11
     logarith
    0.11
     moeda
    0.11
    ◯
    0.11
     marshmallows
    0.11
     países
    0.10
     bourbon
    0.10
    merzen
    0.10
    POSITIVE LOGITS
    ম
    0.11
    আপ
    0.11
    മേ
    0.11
    മ
    0.11
    ಮ
    0.10
     Christine
    0.10
    Captain
    0.10
    İ
    0.10
     మ
    0.10
     Captain
    0.10
    Activations Density 0.001%

    No Known Activations