© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 132308
    Prev
    Next
    INDEX
    Explanations

    gnosis, gather

    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
    in
    1.40
    ко
    1.20
    ни
    1.02
    ু
    1.00
    ня
    0.97
    ра
    0.92
    ని
    0.91
    ί
    0.89
    ুঁ
    0.88
    <0x91>
    0.88
    POSITIVE LOGITS
    r
    1.56
    t
    1.52
    ために
    1.41
    ן
    1.30
    त
    1.25
    های
    1.22
    ها
    1.21
    いた
    1.20
    k
    1.17
    る
    1.17
    Activations Density 0.001%

    No Known Activations