© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46204
    Prev
    Next
    INDEX
    Explanations

    margarine or Marxist

    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_3_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
    يل
    0.63
    mathscr
    0.63
    ساس
    0.61
    ľov
    0.59
    তাস
    0.55
    殄
    0.55
    вая
    0.55
    كي
    0.55
    思議
    0.54
    produksi
    0.54
    POSITIVE LOGITS
     a
    0.87
     and
    0.76
    י
    0.75
    a
    0.75
    );
    0.73
    ING
    0.71
    ম
    0.69
     активность
    0.67
    ן
    0.67
     morphine
    0.66
    Activations Density 0.000%

    No Known Activations