© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131016
    Prev
    Next
    INDEX
    Explanations

    keep it simple instruction

    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_6_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
    i
    1.50
    al
    1.46
    f
    1.41
    y
    1.38
    u
    1.33
    el
    1.32
    v
    1.17
    er
    1.16
    ed
    1.15
    x
    1.13
    POSITIVE LOGITS
    arı
    1.07
    ка
    0.89
    ﺎ
    0.86
     ונ
    0.84
     ও
    0.82
     え
    0.82
    ০০
    0.81
    arıyla
    0.80
     и
    0.79
    時は
    0.78
    Activations Density 0.001%

    No Known Activations