© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108263
    Prev
    Next
    INDEX
    Explanations

    strokes and difficulties

    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_1_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
    .
    1.84
    7
    1.62
    8
    1.60
    6
    1.46
    3
    1.33
    9
    1.27
    4
    1.27
    ру
    1.20
    ‌هایی
    1.20
    ك
    1.18
    POSITIVE LOGITS
    राबरी
    1.07
    見
    1.02
    ദ്ധതി
    1.01
     be
    1.00
    鶚
    0.94
     has
    0.94
    ত্যাশিত
    0.93
    ătoare
    0.93
     was
    0.92
    ine
    0.88
    Activations Density 0.001%

    No Known Activations