© 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. 43018
    Prev
    Next
    INDEX
    Explanations

    Cost of Goods Sold

    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
    s
    1.23
    r
    1.03
    l
    0.98
    us
    0.94
    h
    0.92
    k
    0.92
    b
    0.90
    t
    0.90
    コスト
    0.84
    p
    0.84
    POSITIVE LOGITS
    ج
    0.85
    ش
    0.82
    ول
    0.71
    ం
    0.67
     ઉપયોગ
    0.66
     حسين
    0.64
    نا
    0.63
    }
    0.63
    ку
    0.63
     وأ
    0.62
    Activations Density 0.004%

    No Known Activations