© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13393
    Prev
    Next
    INDEX
    Explanations

    inplace operations

    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_13_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
    ک
    0.39
    2
    0.36
    کت
    0.35
     치
    0.35
    4
    0.34
    ул
    0.34
    water
    0.34
    ž
    0.33
    ウ
    0.33
    cially
    0.32
    POSITIVE LOGITS
    s
    0.44
    ים
    0.35
     lifeline
    0.34
     no
    0.33
     mastery
    0.31
     Creole
    0.30
     bootstrap
    0.30
     context
    0.30
     rewards
    0.30
     trustworthiness
    0.29
    Activations Density 0.089%

    No Known Activations