© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42773
    Prev
    Next
    INDEX
    Explanations

    Jane Smith

    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
    د
    0.86
    O
    0.77
    P
    0.74
    א
    0.70
    فيد
    0.68
    T
    0.67
    お
    0.66
    OF
    0.65
    дят
    0.65
    دين
    0.63
    POSITIVE LOGITS
    ra
    0.81
    ha
    0.72
    ва
    0.69
    ro
    0.66
     guilt
    0.59
    wa
    0.59
    лу
    0.58
    ry
    0.58
    <0xA7>
    0.57
    ii
    0.57
    Activations Density 0.004%

    No Known Activations