© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43884
    Prev
    Next
    INDEX
    Explanations

    HIL, LOC, gard, unn

    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
    '
    0.94
    igan
    0.73
    ushing
    0.71
    ong
    0.68
    í
    0.66
    с
    0.64
    ens
    0.64
    ua
    0.63
    ess
    0.62
    anya
    0.61
    POSITIVE LOGITS
    ي
    1.17
    ה
    1.06
    ه
    1.05
    ი
    0.97
     egip
    0.96
    ر
    0.92
    К
    0.89
    י
    0.84
    ﺍ
    0.80
     medall
    0.79
    Activations Density 0.005%

    No Known Activations