© 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. 24347
    Prev
    Next
    INDEX
    Explanations

    score points

    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
     점
    1.41
    点
    1.23
    점
    1.16
     point
    1.16
     điểm
    1.11
     点
    1.09
    點
    1.06
    点的
    1.00
     نقط
    0.99
    point
    0.98
    POSITIVE LOGITS
    分
    2.19
    分的
    1.79
     分
    1.55
    분
    1.40
    的分
    1.38
     phân
    1.35
    分の
    1.30
     분
    1.19
     roz
    1.17
    분이
    1.15
    Activations Density 0.039%

    No Known Activations