© 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. 195575
    Prev
    Next
    INDEX
    Explanations

    price

    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
     grantor
    0.44
    aków
    0.40
     ডিফ
    0.39
    험
    0.39
    arka
    0.38
    grim
    0.38
     द
    0.38
    字段
    0.38
    angolo
    0.38
    ntgen
    0.37
    POSITIVE LOGITS
    িস
    0.38
    sar
    0.38
    exercises
    0.38
    StartAddress
    0.37
    eward
    0.36
     jay
    0.36
    nutí
    0.35
     Elevator
    0.35
     exercises
    0.34
    媚
    0.34
    Activations Density 0.002%

    No Known Activations