© 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. 62442
    Prev
    Next
    INDEX
    Explanations

    shapeshifted

    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
     de
    1.20
     is
    1.13
    를
    1.02
     pour
    0.97
    大
    0.96
    y
    0.95
    не
    0.95
    ال
    0.95
    ka
    0.92
    al
    0.90
    POSITIVE LOGITS
     for
    1.28
    shifts
    1.13
    SHIFT
    1.09
    স
    1.08
    ু
    1.06
    }
    1.03
    シフト
    1.00
     Shifts
    1.00
    shift
    1.00
    hift
    0.99
    Activations Density 0.001%

    No Known Activations