© 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. 156990
    Prev
    Next
    INDEX
    Explanations

    EleutherAI, Eleanor, elephants, elegy

    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
    0
    1.08
    ０
    0.94
    ли
    0.92
    와의
    0.91
    <0x80>
    0.86
    те
    0.85
    ের
    0.83
    رى
    0.83
    нус
    0.83
    اة
    0.83
    POSITIVE LOGITS
     to
    1.74
     on
    1.59
     at
    1.54
     of
    1.30
     in
    1.23
     (
    1.21
    い
    1.17
    この
    1.14
    し
    1.13
     instal
    1.05
    Activations Density 0.001%

    No Known Activations