© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236197
    Prev
    Next
    INDEX
    Explanations

    param

    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_32_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
    第四
    0.43
     ষষ্ঠ
    0.43
    ullie
    0.42
    第
    0.42
    第六
    0.41
     thứ
    0.40
     offsets
    0.40
    pagination
    0.40
    fifth
    0.40
     nth
    0.39
    POSITIVE LOGITS
    ObjectTemp
    0.41
    гон
    0.39
    setAlignment
    0.38
    RetValue
    0.38
     sanction
    0.37
     vap
    0.37
    BuildAction
    0.36
     কন
    0.35
    🚮
    0.35
    THRESH
    0.35
    Activations Density 0.003%

    No Known Activations