© 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. 39364
    Prev
    Next
    INDEX
    Explanations

    event type

    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
    ال
    0.87
    ح
    0.87
    し
    0.82
    ො
    0.81
    ت
    0.79
    fb
    0.76
    ه
    0.73
    oj
    0.72
    fZ
    0.72
    freq
    0.71
    POSITIVE LOGITS
     nessa
    0.71
    I
    0.70
     unimagin
    0.68
     conceivably
    0.68
     hillside
    0.66
    อย่าง
    0.63
     detour
    0.61
    ם
    0.61
     deste
    0.60
     lingering
    0.59
    Activations Density 0.018%

    No Known Activations