© 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. 48835
    Prev
    Next
    INDEX
    Explanations

    sp

    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
    olve
    0.38
     Tij
    0.38
    鳕
    0.38
     Estat
    0.37
     دیا
    0.37
    eliminate
    0.37
    Defendant
    0.35
     شوف
    0.35
     tartoz
    0.34
     Appraisal
    0.34
    POSITIVE LOGITS
    วง
    0.41
    Responder
    0.38
     contextos
    0.37
    壘
    0.37
     oregano
    0.37
     limiting
    0.36
    Ore
    0.36
     सर्किल
    0.36
     sen
    0.35
     frivol
    0.35
    Activations Density 0.005%

    No Known Activations