© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205219
    Prev
    Next
    INDEX
    Explanations

    It

    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_56_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
     י
    0.65
    יית
    0.57
    ית
    0.52
    you
    0.49
     य
    0.46
     ย
    0.43
     You
    0.42
     IT
    0.42
    YOU
    0.42
     you
    0.40
    POSITIVE LOGITS
     potentials
    0.43
     Poss
    0.38
    Poss
    0.37
    Ve
    0.37
    可能性
    0.36
     Potential
    0.35
    म्म
    0.34
    мма
    0.34
     찾
    0.34
     ஆட்ச
    0.34
    Activations Density 0.002%

    No Known Activations