© 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. 143538
    Prev
    Next
    INDEX
    Explanations

    touch the

    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
    น
    1.52
    ’
    1.45
    のは
    1.31
    का
    1.28
    وی
    1.28
    νε
    1.23
    та
    1.22
     that
    1.18
    വ
    1.18
    اری
    1.17
    POSITIVE LOGITS
    b
    1.75
    ل
    1.51
    d
    1.27
    går
    1.16
    gård
    1.13
    ból
    1.09
    ال
    1.08
    gående
    1.08
    beweg
    1.07
    p
    1.07
    Activations Density 0.000%

    No Known Activations