© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167915
    Prev
    Next
    INDEX
    Explanations

    direct - service/channel

    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_34_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
    disconnected
    0.38
    indexOf
    0.37
     WordPerfect
    0.37
     defocus
    0.36
     $("<
    0.36
    autogui
    0.35
    děpodob
    0.35
     toBe
    0.35
    vrir
    0.35
     Итали
    0.34
    POSITIVE LOGITS
     swims
    0.42
     спокойно
    0.39
     centrally
    0.37
     calmly
    0.37
     chess
    0.36
     problemlos
    0.36
    ｏ
    0.36
     alz
    0.35
     Wissen
    0.35
    櫳
    0.35
    Activations Density 0.006%

    No Known Activations