© 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. 122835
    Prev
    Next
    INDEX
    Explanations

    purr-fect / purr-ple

    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
    ב
    0.86
    то
    0.80
     as
    0.79
     İyi
    0.74
    כ
    0.74
    ט
    0.71
    ات
    0.71
    ת
    0.71
    द
    0.69
    기
    0.69
    POSITIVE LOGITS
    s
    0.73
     totaled
    0.72
    ্বা
    0.67
    (#
    0.64
    er
    0.64
     risked
    0.64
     পেয়েছিলাম
    0.63
     fooled
    0.63
     totalled
    0.63
    uje
    0.62
    Activations Density 0.000%

    No Known Activations