© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50693
    Prev
    Next
    INDEX
    Explanations

    code blocks and libraries

    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
     gain
    0.42
     ؟
    0.36
     جس
    0.35
     nine
    0.35
     epist
    0.35
     oste
    0.34
     tandis
    0.34
    姣
    0.34
     strept
    0.34
    ਸੀ
    0.34
    POSITIVE LOGITS
    räge
    0.40
    reff
    0.37
     führt
    0.36
     చూ
    0.36
    मैं
    0.35
    ้น
    0.35
     recalled
    0.35
    ucks
    0.35
     राहुल
    0.34
     Leia
    0.34
    Activations Density 0.009%

    No Known Activations