© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79392
    Prev
    Next
    INDEX
    Explanations

    pro/fro prefix

    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_53_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
    フェ
    0.93
    pos
    0.68
    фе
    0.68
    fes
    0.66
    페
    0.66
    Fe
    0.65
     фе
    0.65
    f
    0.64
    pose
    0.63
     fé
    0.61
    POSITIVE LOGITS
    Ot
    0.70
     Ot
    0.66
     ot
    0.64
     OT
    0.57
     Otis
    0.56
    ot
    0.52
     Te
    0.52
     te
    0.52
    OT
    0.51
    OTC
    0.51
    Activations Density 0.024%

    No Known Activations