© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41154
    Prev
    Next
    INDEX
    Explanations

    `\/` followed by punctuation or code snippets

    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
    t
    1.02
    м
    0.92
    و
    0.88
    ت
    0.86
    os
    0.83
    n
    0.82
    ուս
    0.82
    ى
    0.80
    েন
    0.79
    nál
    0.78
    POSITIVE LOGITS
    '
    1.44
    /
    0.93
    '।
    0.82
    :
    0.80
    -
    0.80
    '/>
    0.79
     et
    0.75
    Α
    0.72
    West
    0.72
    ’
    0.72
    Activations Density 0.002%

    No Known Activations