© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11116
    Prev
    Next
    INDEX
    Explanations

    code documentation /**

    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_13_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
    \
    0.18
    िरिक्स
    0.18
     totalling
    0.17
     음악
    0.17
    -*
    0.17
    -<
    0.17
     나누
    0.16
    ⟢
    0.16
     TER
    0.16
    baud
    0.16
    POSITIVE LOGITS
    ro
    0.21
    čky
    0.17
    tow
    0.17
     McDonnell
    0.17
    acée
    0.16
    াকে
    0.16
    cje
    0.16
    ServiceObject
    0.16
    rière
    0.16
    age
    0.16
    Activations Density 0.103%

    No Known Activations