© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103634
    Prev
    Next
    INDEX
    Explanations

    V/f control

    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_1_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
    2.00
    ة
    1.08
     résident
    0.99
    0.89
     démar
    0.88
    an
    0.86
    مة
    0.86
     gamut
    0.83
     réd
    0.83
     travail
    0.82
    POSITIVE LOGITS
    ون
    1.44
    ุ
    1.38
    時間は
    1.18
    一緒に
    1.16
    গ
    1.15
    ای
    1.14
    のに
    1.11
    am
    1.07
    ל
    1.05
    很是
    1.05
    Activations Density 0.003%

    No Known Activations