© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230805
    Prev
    Next
    INDEX
    Explanations

    striders, strigil, strass, stracciatella, strnuous, stridor, strigoi, straddle, stinger

    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_6_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
    on
    1.33
    as
    1.25
     of
    1.25
    า
    1.23
     that
    1.13
    that
    1.10
    ur
    1.09
    of
    1.05
    a
    1.03
    ش
    1.03
    POSITIVE LOGITS
    도
    1.20
    も
    1.13
    も含
    1.12
    に使
    1.02
     старосног
    0.96
    もら
    0.96
     руководством
    0.95
    ও
    0.94
     گے۔
    0.91
    ljivo
    0.91
    Activations Density 0.000%

    No Known Activations