© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106893
    Prev
    Next
    INDEX
    Explanations

    analysis and review

    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
    ی
    1.31
    ים
    1.25
    ก
    1.25
    ला
    1.22
     and
    1.21
    ম
    1.21
    ם
    1.21
    𝑠
    1.20
    مین
    1.13
    ालय
    1.09
    POSITIVE LOGITS
    _
    1.45
    '
    1.34
    <0x80>
    1.05
    ut
    0.99
    Definition
    0.95
    '/>
    0.94
    h
    0.94
    ri
    0.91
    w
    0.90
    ö
    0.90
    Activations Density 0.000%

    No Known Activations