© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36345
    Prev
    Next
    INDEX
    Explanations

    multiple choice answers

    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_31_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
    Definitions
    0.39
    કરણ
    0.38
     trust
    0.37
    trust
    0.37
    帯
    0.37
    ChooseCharacter
    0.36
     পাশ্চাত্য
    0.36
    晝
    0.35
    ahari
    0.35
    ုံ
    0.35
    POSITIVE LOGITS
     disulfide
    0.38
     tale
    0.37
    tale
    0.36
     Републи
    0.36
     लगाए
    0.36
     ediciones
    0.36
     Diss
    0.36
     adversarial
    0.36
    ແ
    0.36
     textes
    0.34
    Activations Density 0.001%

    No Known Activations