© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36189
    Prev
    Next
    INDEX
    Explanations

    dear salutations

    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_11_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
    細胞
    0.64
    وم
    0.58
    গ্ধ
    0.56
    ير
    0.55
    راح
    0.55
    ग्ध
    0.55
    و
    0.54
    บวน
    0.54
    бою
    0.53
    нови
    0.53
    POSITIVE LOGITS
     towards
    0.58
     to
    0.55
     μ
    0.54
     waxes
    0.54
     де
    0.53
     aga
    0.53
     inco
    0.52
     ут
    0.52
     at
    0.52
    '])
    0.52
    Activations Density 0.003%

    No Known Activations