© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54499
    Prev
    Next
    INDEX
    Explanations

    holy fuck

    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_55_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
    ppings
    0.46
     shitty
    0.43
     fucking
    0.40
    ute
    0.38
    パリ
    0.38
    assade
    0.37
    種
    0.37
    yn
    0.36
    कद
    0.36
    fuck
    0.36
    POSITIVE LOGITS
    Sta
    0.39
     пора
    0.38
     moul
    0.38
    IZER
    0.37
     magnetized
    0.36
     magnet
    0.36
     pou
    0.35
     globally
    0.35
     Sta
    0.35
     dobbiamo
    0.35
    Activations Density 0.056%

    No Known Activations