© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130530
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts

    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
    س
    1.28
    א
    1.10
    ك
    1.09
    ;
    1.08
    ל
    1.06
    (
    1.05
    ilt
    1.01
    )،
    0.97
    स
    0.94
    ates
    0.94
    POSITIVE LOGITS
     is
    1.02
    рия
    0.85
    ONOM
    0.84
    ется
    0.82
    AN
    0.81
    ER
    0.80
    ната
    0.80
     Timatic
    0.76
    ത്തന
    0.75
     branca
    0.74
    Activations Density 0.000%

    No Known Activations