© 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. 155483
    Prev
    Next
    INDEX
    Explanations

    business and legal structures

    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
    CTT
    0.39
    ORMAL
    0.37
     Высо
    0.36
    oczes
    0.36
    묽
    0.36
    蠕
    0.35
    denomination
    0.35
    营业
    0.35
     उ
    0.35
    Hight
    0.35
    POSITIVE LOGITS
     Blazer
    0.45
    trusive
    0.40
     ફે
    0.40
    瘍
    0.39
    挾
    0.39
    нией
    0.39
     Blazers
    0.39
    TEGER
    0.38
     tera
    0.38
     паро
    0.37
    Activations Density 0.000%

    No Known Activations