© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34517
    Prev
    Next
    INDEX
    Explanations

    Tech model names

    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_50_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
    phin
    0.40
    issons
    0.39
     Ville
    0.38
     numberWithFloat
    0.37
     socketList
    0.37
    CS
    0.36
    \},
    0.36
    Vin
    0.36
    städ
    0.36
    ozu
    0.36
    POSITIVE LOGITS
     Jab
    0.49
     المبار
    0.46
     ku
    0.45
     கு
    0.43
     Mub
    0.42
     Ahm
    0.42
     Mubarak
    0.41
     J
    0.40
     Ku
    0.39
     Haw
    0.39
    Activations Density 0.003%

    No Known Activations