© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68925
    Prev
    Next
    INDEX
    Explanations

    say webcomic names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     cartoon
    0.48
     Cartoon
    0.44
    Cartoon
    0.42
    ཤ
    0.37
     cartoonist
    0.37
    masht
    0.37
    cartoon
    0.37
     एपिसोड
    0.36
    auche
    0.36
    Manus
    0.36
    POSITIVE LOGITS
    银
    0.40
    Ợ
    0.40
    CaO
    0.39
    iería
    0.39
     Star
    0.38
    ambuco
    0.38
     CaO
    0.38
    нология
    0.38
    ног
    0.36
     mornings
    0.35
    Activations Density 0.001%

    No Known Activations