© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214580
    Prev
    Next
    INDEX
    Explanations

    calls or summons

    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_5_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
    は
    1.38
    is
    1.30
    కు
    1.27
    는
    1.23
    은
    1.23
    9
    1.22
    어
    1.20
    ли
    1.19
     that
    1.16
    The
    1.15
    POSITIVE LOGITS
    <0x80>
    1.30
     (
    1.15
     financi
    1.11
     permanente
    1.00
    璜
    1.00
    aq
    0.99
    ilj
    0.99
    y
    0.99
    yta
    0.98
     Termin
    0.97
    Activations Density 0.002%

    No Known Activations