© 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. 35869
    Prev
    Next
    INDEX
    Explanations

    length and width definitions

    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
    ру
    0.80
    ва
    0.78
    们
    0.75
    ும்
    0.73
    ги
    0.71
    া
    0.70
     trách
    0.68
    ो
    0.68
    ığı
    0.67
     dịch
    0.66
    POSITIVE LOGITS
    ק
    0.60
    鋆
    0.59
    ast
    0.58
    cido
    0.57
    Sig
    0.56
    ริญ
    0.55
    (
    0.55
    叁
    0.55
    cN
    0.54
    coe
    0.54
    Activations Density 0.002%

    No Known Activations