© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258495
    Prev
    Next
    INDEX
    Explanations

    php plugin metadata /**

    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_22_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
    َد
    0.51
    پیگنڈ
    0.48
    妒
    0.42
    َل
    0.41
    цией
    0.40
    ቄ
    0.40
    QRSTUVWXYZ
    0.40
    pupp
    0.40
    pz
    0.39
    replaced
    0.39
    POSITIVE LOGITS
     μ
    0.48
     processes
    0.47
     প্রক্রিয়া
    0.46
     struggles
    0.42
     Notes
    0.42
     possibilities
    0.41
     pursuit
    0.41
    維持
    0.41
     Comprehensive
    0.41
     implications
    0.40
    Activations Density 0.000%

    No Known Activations