© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36064
    Prev
    Next
    INDEX
    Explanations

    attacks

    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
    掰
    0.41
    ETY
    0.39
     tal
    0.39
    ચી
    0.38
    ството
    0.38
     SAF
    0.38
    тре
    0.37
    埼
    0.37
     Saf
    0.37
    answ
    0.36
    POSITIVE LOGITS
     kis
    0.49
     ü
    0.41
     ment
    0.40
     ments
    0.39
     vis
    0.39
    munk
    0.38
    zs
    0.38
    ült
    0.38
     விட்ட
    0.38
    くな
    0.38
    Activations Density 0.001%

    No Known Activations