© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14241
    Prev
    Next
    INDEX
    Explanations

    normal quality, NormalFloat, Normalizing Flows, normal distribution

    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
    㠱
    0.43
     iOS
    0.42
     JEE
    0.42
     एंड्र
    0.42
    抗
    0.41
    rophe
    0.38
    ሑ
    0.38
     tracks
    0.37
     Tracks
    0.37
     Relay
    0.37
    POSITIVE LOGITS
    regist
    0.42
    indicators
    0.36
     regist
    0.36
    Mate
    0.36
    indic
    0.36
     شدم
    0.35
    眅
    0.35
     пси
    0.34
     indic
    0.34
    Indic
    0.34
    Activations Density 0.000%

    No Known Activations