© 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. 206784
    Prev
    Next
    INDEX
    Explanations

    data types

    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
    heder
    0.40
     અસર
    0.39
     Nigerians
    0.36
    <unused99>
    0.36
    ிறார்கள்
    0.36
    ecção
    0.35
     bevorzug
    0.35
     கண்காணி
    0.35
    inflammation
    0.34
    arankan
    0.34
    POSITIVE LOGITS
    Domain
    0.38
     pursue
    0.36
     taking
    0.36
    ORTS
    0.36
    Dist
    0.35
    Digital
    0.35
    ،
    0.34
    칭
    0.34
    entures
    0.34
    ष्‍ट
    0.34
    Activations Density 0.000%

    No Known Activations