© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49079
    Prev
    Next
    INDEX
    Explanations

    average depth

    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_31_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
    SqlDbType
    0.38
    راط
    0.37
     ámbito
    0.36
     produ
    0.35
    đenje
    0.35
    produksi
    0.34
    ിക്കാം
    0.34
     ર
    0.34
     Rates
    0.34
     آئینہ
    0.33
    POSITIVE LOGITS
    年龄
    0.92
     age
    0.91
    年齢
    0.86
    Age
    0.82
     Age
    0.81
     AGE
    0.74
     aged
    0.73
     aging
    0.72
     âge
    0.72
     возраст
    0.72
    Activations Density 0.025%

    No Known Activations