© 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. 122843
    Prev
    Next
    INDEX
    Explanations

    design and construction

    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
    。
    0.91
    3
    0.73
    ।
    0.67
    。.
    0.64
    。",
    0.64
    面膜
    0.63
    ۔
    0.61
     لأ
    0.60
    )。
    0.60
    textepsilon
    0.58
    POSITIVE LOGITS
    ’
    0.70
     categor
    0.67
     sanit
    0.65
    ing
    0.61
    প
    0.61
    ան
    0.61
    ü
    0.61
    ط
    0.60
     parasit
    0.59
    '
    0.59
    Activations Density 0.001%

    No Known Activations