© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145211
    Prev
    Next
    INDEX
    Explanations

    Omni- prefix words

    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_0_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
    7
    2.09
    8
    2.05
    1
    1.98
    9
    1.94
    n
    1.84
    6
    1.68
     at
    1.59
    s
    1.59
    4
    1.55
    5
    1.53
    POSITIVE LOGITS
    ри
    2.59
    ী
    2.13
    ை
    1.75
    ת
    1.63
    ле
    1.54
     accentuate
    1.54
    ির
    1.51
     veliki
    1.48
    תה
    1.43
    рино
    1.41
    Activations Density 0.001%

    No Known Activations