© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161230
    Prev
    Next
    INDEX
    Explanations

    aloofness and gusto mong

    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_2_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
    م
    1.34
    ب
    1.28
    いた
    1.16
    க்கு
    1.15
    ك
    1.15
    氇
    1.09
     on
    1.04
     to
    1.03
    يل
    0.98
    使い方
    0.98
    POSITIVE LOGITS
    i
    1.34
    ู
    1.33
    ри
    1.31
    ;
    1.29
    a
    1.27
    G
    1.25
    is
    1.20
    D
    1.20
    ه
    1.20
    ↵↵
    1.16
    Activations Density 0.000%

    No Known Activations