© 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
    2. Gemma-3-27B-IT
    3. 24-GEMMASCOPE-2-TRANSCODER-262K
    4. 178162
    Prev
    Next
    INDEX
    Explanations

    youtube.com/playlist?list=

    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_24_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
     competing
    0.42
     }
    0.42
    యోజ
    0.38
    [
    0.37
     politically
    0.36
    bounds
    0.35
     competitor
    0.35
    <0x80>
    0.35
     guarantees
    0.35
    儼
    0.35
    POSITIVE LOGITS
     Illness
    0.39
     हरे
    0.39
     illness
    0.38
     Elo
    0.38
     malattie
    0.38
     tę
    0.38
    死亡
    0.37
     lẽ
    0.37
    "]),
    0.37
     misdeme
    0.37
    Activations Density 0.001%

    No Known Activations