© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4271
    Prev
    Next
    INDEX
    Explanations

    ac prefix

    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_40_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
    ப்பிட
    0.38
    ंद
    0.35
    antan
    0.35
    گزاری
    0.34
     ബ
    0.33
     buoy
    0.33
    常に
    0.33
     certains
    0.32
    बीसी
    0.32
     معي
    0.32
    POSITIVE LOGITS
    Ac
    0.44
    ronym
    0.42
     acidic
    0.41
     الاك
    0.39
     Acosta
    0.38
    <0x92>
    0.37
    ademia
    0.37
     ακ
    0.37
     acumin
    0.37
    quirements
    0.37
    Activations Density 0.220%

    No Known Activations