© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236455
    Prev
    Next
    INDEX
    Explanations

    etc

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    々
    0.37
    々は
    0.37
    essentially
    0.36
     essentially
    0.35
     Essentially
    0.35
    ¶
    0.34
    Essentially
    0.34
    include
    0.33
    槽
    0.33
    след
    0.32
    POSITIVE LOGITS
    oline
    0.37
     Cá
    0.35
     cá
    0.35
    อยาก
    0.35
     Turbo
    0.35
    igel
    0.35
    หัส
    0.34
     ശിഷ്യ
    0.34
     oportunidad
    0.34
    ష్య
    0.34
    Activations Density 0.003%

    No Known Activations