© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31232
    Prev
    Next
    INDEX
    Explanations

    icefall, mountains, training

    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
    RuL
    0.39
     Crocker
    0.36
     Shift
    0.36
     Bo
    0.35
    茁
    0.35
     Мол
    0.35
    鱒
    0.35
     Spaghetti
    0.35
    転
    0.35
     Pud
    0.34
    POSITIVE LOGITS
     ट्रेनिंग
    0.41
    ステンレス
    0.39
    ক্রম
    0.36
    জাতি
    0.35
     kän
    0.35
     matchmaking
    0.35
     TRAINING
    0.35
     fill
    0.35
     लेख
    0.35
    手順
    0.34
    Activations Density 0.010%

    No Known Activations