© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68378
    Prev
    Next
    INDEX
    Explanations

    programming and tech

    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_46_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
     tú
    0.45
    ⑵
    0.41
    athu
    0.40
    Half
    0.38
    EXTRA
    0.35
    SW
    0.35
    ক্টো
    0.34
    ABA
    0.34
    を受
    0.34
    Coding
    0.34
    POSITIVE LOGITS
    语言
    0.40
    崴
    0.40
     물질
    0.39
     Brush
    0.38
     промежу
    0.38
    赂
    0.38
    مدة
    0.37
     brush
    0.37
    离子
    0.37
    Cmd
    0.37
    Activations Density 0.010%

    No Known Activations