© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198423
    Prev
    Next
    INDEX
    Explanations

    collectors, cases, Board, TextBox

    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_15_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
    0
    0.57
    自由
    0.54
    1
    0.54
    든
    0.53
    KZ
    0.52
    青
    0.52
    数组
    0.51
    접
    0.51
    रिपोर्ट
    0.50
    VEST
    0.49
    POSITIVE LOGITS
     carburetor
    0.60
     effiz
    0.59
     Cand
    0.58
     Years
    0.57
     GPT
    0.55
     நூற்றாண்டின்
    0.55
    𝘢
    0.55
     Lebanon
    0.54
     Puis
    0.54
     Massachusetts
    0.54
    Activations Density 0.004%

    No Known Activations