© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171403
    Prev
    Next
    INDEX
    Explanations

    state is off

    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_20_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
    ມັນ
    0.36
    Altitude
    0.36
     फ्लाइट
    0.34
    準備
    0.33
    ґ
    0.33
     ऊंचाई
    0.32
    它
    0.32
    ิม
    0.32
    迫
    0.32
    鮋
    0.32
    POSITIVE LOGITS
    la
    0.39
    ita
    0.39
    ari
    0.37
     santos
    0.36
    been
    0.35
     maintain
    0.35
     using
    0.35
     bring
    0.35
    bb
    0.34
    maintain
    0.34
    Activations Density 0.001%

    No Known Activations