© 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. 130168
    Prev
    Next
    INDEX
    Explanations

    bus

    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
     చేపట్ట
    0.43
     v
    0.43
    ullie
    0.42
     wallet
    0.40
     cadets
    0.39
    㽚
    0.39
    Cad
    0.38
     বর্বর
    0.38
     Sp
    0.38
     dall
    0.38
    POSITIVE LOGITS
     NA
    0.40
    urschutz
    0.40
    纳米
    0.39
    湎
    0.38
    NA
    0.38
     अंध
    0.36
    集体
    0.36
    мей
    0.36
     న
    0.36
    IENT
    0.36
    Activations Density 0.000%

    No Known Activations