© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63582
    Prev
    Next
    INDEX
    Explanations

    say "*"

    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_59_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
     Smooth
    0.33
     correspondance
    0.32
    ृ
    0.32
    رق
    0.31
    ろしく
    0.31
    Capable
    0.31
    Smooth
    0.31
     recor
    0.31
     DISCLAIMED
    0.31
     koost
    0.30
    POSITIVE LOGITS
    🧍
    0.40
    sterling
    0.38
    σκε
    0.37
    ("'
    0.36
    sing
    0.36
    hed
    0.35
    waukee
    0.35
    भंगा
    0.35
     வகையான
    0.35
     ειδ
    0.35
    Activations Density 0.052%

    No Known Activations