© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166151
    Prev
    Next
    INDEX
    Explanations

    dogma

    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_31_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
     fenomeno
    0.47
     Physician
    0.42
    텀
    0.42
    ությունը
    0.41
     fenómenos
    0.39
     fenómeno
    0.39
    募集
    0.38
     Испа
    0.38
     язык
    0.38
     bistouri
    0.37
    POSITIVE LOGITS
     সেট
    0.38
     giv
    0.37
    រ
    0.36
    Vern
    0.35
    三人
    0.35
    odhya
    0.35
     armazenamento
    0.34
    Three
    0.34
     pampered
    0.33
     paint
    0.33
    Activations Density 0.000%

    No Known Activations