© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53766
    Prev
    Next
    INDEX
    Explanations

    environment variable keys

    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_30_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
     obedience
    0.42
     false
    0.38
    櫚
    0.36
     لم
    0.35
    覓
    0.35
     standards
    0.34
     Southwestern
    0.34
     جنوب
    0.33
    タイヤ
    0.33
     southernmost
    0.32
    POSITIVE LOGITS
    inear
    0.41
    ্তার
    0.38
    แล้ว
    0.36
     announc
    0.36
     ഇപ്പോള്‍
    0.36
    Jetzt
    0.36
     curtain
    0.35
     ಮತ್ತೆ
    0.35
    ឮ
    0.35
    hx
    0.35
    Activations Density 0.000%

    No Known Activations