© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87173
    Prev
    Next
    INDEX
    Explanations

    Chao Fan comics Head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    o
    0.75
    y
    0.75
    s
    0.73
    ה
    0.70
    เป็น
    0.70
    รับ
    0.69
    i
    0.69
    ে
    0.69
            
    0.68
    ]
    0.66
    POSITIVE LOGITS
    迂
    0.63
    ícito
    0.59
    йки
    0.56
    訒
    0.56
    獧
    0.56
    јединачна
    0.55
    වුන්
    0.54
    kušen
    0.54
     Condiciones
    0.54
    傢
    0.54
    Activations Density 0.000%

    No Known Activations