© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33465
    Prev
    Next
    INDEX
    Explanations

    Coin sides

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Ontario
    0.41
    tree
    0.40
    睡觉
    0.38
    gar
    0.38
    уса
    0.37
    直
    0.36
     የእ
    0.36
    clipse
    0.35
    乌
    0.35
    Ꮃ
    0.34
    POSITIVE LOGITS
     পক্ষের
    0.46
    ahue
    0.46
     Coin
    0.44
    古墳
    0.42
     მხ
    0.42
    чиго
    0.40
    חות
    0.40
     lados
    0.39
     сторо
    0.39
    Coin
    0.39
    Activations Density 0.000%

    No Known Activations