© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64094
    Prev
    Next
    INDEX
    Explanations

    silent twelve

    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_46_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
     idealism
    0.38
    蓍
    0.38
     SNA
    0.37
     adversity
    0.36
     happy
    0.36
    whal
    0.36
     eyewear
    0.35
     exerting
    0.35
     FIFO
    0.35
    扱
    0.35
    POSITIVE LOGITS
    Silent
    0.66
     Silent
    0.62
     silent
    0.58
    silent
    0.56
     Twelve
    0.54
    十二
    0.53
     twelve
    0.52
     douze
    0.48
     १२
    0.47
     ১২
    0.47
    Activations Density 0.000%

    No Known Activations