© 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. 195790
    Prev
    Next
    INDEX
    Explanations

    and

    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
    aughters
    0.38
     ад
    0.38
     ret
    0.38
    잖
    0.38
     Bans
    0.37
    不死
    0.37
     അധ
    0.37
     STUDY
    0.36
     Ret
    0.36
     Ban
    0.35
    POSITIVE LOGITS
    流
    0.40
     kih
    0.40
    ப்படுக
    0.39
     Hayden
    0.39
     डीएस
    0.38
    VOA
    0.38
    Hay
    0.38
     DS
    0.38
     barley
    0.37
     सिविल
    0.37
    Activations Density 0.003%

    No Known Activations