© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42294
    Prev
    Next
    INDEX
    Explanations

    Lime or Limbs

    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_3_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
    س
    1.02
     It
    0.82
    It
    0.77
    یس
    0.75
    ید
    0.72
    ス
    0.72
    سر
    0.71
     to
    0.70
    ס
    0.70
    с
    0.70
    POSITIVE LOGITS
    e
    0.67
    ave
    0.66
    asının
    0.66
    ed
    0.65
    at
    0.63
     minimize
    0.61
     زين
    0.59
    ev
    0.57
     يك
    0.57
     ngân
    0.56
    Activations Density 0.001%

    No Known Activations