© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104842
    Prev
    Next
    INDEX
    Explanations

    Dianabol, Dunning, Dharma

    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_1_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
    л
    1.41
    س
    1.25
    т
    1.23
    д
    1.23
    ла
    1.17
    imed
    1.12
    с
    1.07
    ль
    1.06
    ž
    1.06
    ,
    1.05
    POSITIVE LOGITS
    Ди
    1.13
     renormal
    1.09
     by
    1.07
    ી
    1.01
     categor
    0.97
    0
    0.97
     Ди
    0.96
    其他
    0.95
     résult
    0.90
    n
    0.89
    Activations Density 0.000%

    No Known Activations