© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195829
    Prev
    Next
    INDEX
    Explanations

    job

    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
     Orton
    0.42
    پر
    0.42
     Hell
    0.41
    oss
    0.40
    藓
    0.40
     optimality
    0.39
    સાર
    0.38
    Fight
    0.38
     amplifying
    0.38
    permissionid
    0.38
    POSITIVE LOGITS
     الدولي
    0.39
     amu
    0.38
    唓
    0.36
    ationen
    0.36
     myocardium
    0.36
    RIO
    0.35
    Anno
    0.34
     యూని
    0.34
    烁
    0.34
     superiores
    0.34
    Activations Density 0.001%

    No Known Activations