© 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. 108003
    Prev
    Next
    INDEX
    Explanations

    exorcism, exemption, skateboard

    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
    ב
    1.70
    ın
    1.38
    ও
    1.34
    ের
    1.28
    and
    1.23
    ut
    1.20
    ם
    1.19
    কে
    1.15
    ی
    1.13
     wynosi
    1.12
    POSITIVE LOGITS
    ام
    1.11
    1.09
     of
    1.05
    sembling
    1.02
    aking
    0.98
    tering
    0.95
    dale
    0.92
    esse
    0.90
     is
    0.85
    ried
    0.85
    Activations Density 0.001%

    No Known Activations