© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45473
    Prev
    Next
    INDEX
    Explanations

    empty it, empty jug

    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_22_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
    0.41
     действительно
    0.40
     QR
    0.37
     좋아
    0.37
     contrário
    0.37
     unlike
    0.37
     over
    0.37
     é
    0.37
    オープ
    0.36
     Voluntary
    0.36
    POSITIVE LOGITS
    selfobj
    0.41
    ':[
    0.41
    ตน
    0.39
    ရော
    0.39
    utérus
    0.39
    *****",
    0.38
     মিডি
    0.38
    নিজের
    0.38
    presentable
    0.38
    ٤
    0.38
    Activations Density 0.000%

    No Known Activations