© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116645
    Prev
    Next
    INDEX
    Explanations

    question phrases

    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_27_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
     न्यूनतम
    0.49
     महाराजा
    0.40
     ন্যূনতম
    0.38
     시절
    0.37
    的关键
    0.36
     галакти
    0.36
    蚁
    0.36
     ಅತ್ಯ
    0.36
     అలాంటి
    0.36
     गुला
    0.36
    POSITIVE LOGITS
     mai
    0.38
    枠
    0.37
    href
    0.35
     "
    0.35
     gps
    0.34
     also
    0.33
     response
    0.33
     également
    0.33
     Laund
    0.32
     nice
    0.32
    Activations Density 0.004%

    No Known Activations