© 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. 104729
    Prev
    Next
    INDEX
    Explanations

    clear understanding or trend

    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
     for
    1.40
    at
    1.26
    ur
    1.20
    ä
    1.19
    1
    1.13
    يد
    1.09
    وم
    1.08
     from
    1.07
    مة
    1.04
    ot
    1.03
    POSITIVE LOGITS
    <0x80>
    1.27
    ۰
    1.00
    ີ້
    0.82
    ின்
    0.82
     друга
    0.79
    きた
    0.79
    جو
    0.77
    дка
    0.77
     допо
    0.76
    지
    0.75
    Activations Density 0.005%

    No Known Activations