© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170028
    Prev
    Next
    INDEX
    Explanations

    say "y" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ডেস্ক
    0.40
    公子
    0.37
    පත්
    0.36
     ܘ
    0.36
    igations
    0.35
    auro
    0.35
    鋏
    0.35
     அம்பேத்கர்
    0.35
     pracuje
    0.35
     обладает
    0.35
    POSITIVE LOGITS
    CU
    0.39
     nigh
    0.37
     Utama
    0.37
     roma
    0.35
     duty
    0.35
     spanish
    0.35
    ‐
    0.35
     Duty
    0.35
    Duty
    0.35
    Us
    0.34
    Activations Density 0.000%

    No Known Activations