© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104599
    Prev
    Next
    INDEX
    Explanations

    handheld

    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
    T
    1.16
    。
    1.16
    M
    1.09
    ،
    1.09
    dy
    1.05
    ।
    1.04
    dt
    1.02
    dr
    1.00
    ，
    1.00
     factors
    1.00
    POSITIVE LOGITS
    м
    1.66
    م
    1.34
    з
    1.20
    ك
    1.19
    il
    1.15
     connu
    1.15
     posiblemente
    1.13
    ம்
    1.13
     tampoco
    1.11
     extraordinaria
    1.11
    Activations Density 0.000%

    No Known Activations