© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210914
    Prev
    Next
    INDEX
    Explanations

    ToTensor()

    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_5_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
    स
    1.34
    น
    1.27
    (
    1.24
     (
    1.23
    ن
    1.16
    г
    1.12
    هم
    1.10
    д
    1.10
    ม
    1.08
    ق
    1.02
    POSITIVE LOGITS
    at
    1.30
    ON
    1.05
    el
    1.02
    ed
    1.01
    UT
    0.99
    அந்த
    0.99
    os
    0.98
     weiß
    0.96
    on
    0.96
    elog
    0.93
    Activations Density 0.001%

    No Known Activations