© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208362
    Prev
    Next
    INDEX
    Explanations

    academic abbreviations

    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_25_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
     puff
    0.38
    А
    0.38
    <0xAF>
    0.38
     larynx
    0.38
    சித்த
    0.37
    ア
    0.37
     wiring
    0.37
    О
    0.37
    動作
    0.37
    Objects
    0.37
    POSITIVE LOGITS
    िलाई
    0.46
     उम्मीदवार
    0.45
    quee
    0.43
    绦
    0.43
     samedi
    0.41
    uesday
    0.41
     vendredi
    0.40
     sabato
    0.40
     ပါ
    0.39
     Grilled
    0.39
    Activations Density 0.000%

    No Known Activations