© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81576
    Prev
    Next
    INDEX
    Explanations

    code interpolation `{{`

    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
    t
    2.16
    m
    2.03
    r
    1.95
    l
    1.61
    w
    1.56
    <0x80>
    1.48
    n
    1.24
    il
    1.23
    ol
    1.23
    ৫
    1.22
    POSITIVE LOGITS
    ك
    1.65
    на
    1.34
    6
    1.33
    ార
    1.27
    를
    1.24
    ب
    1.21
    지
    1.20
    8
    1.17
    나
    1.17
    रा
    1.16
    Activations Density 0.000%

    No Known Activations