© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178774
    Prev
    Next
    INDEX
    Explanations

    Guidelines

    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_50_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
    prav
    0.41
    寨
    0.38
    嗪
    0.37
    たつ
    0.37
     Inter
    0.37
     ЗА
    0.37
    Prog
    0.36
     ザ
    0.36
     pubescence
    0.35
    henburg
    0.35
    POSITIVE LOGITS
    Bent
    0.47
     Bent
    0.41
     bent
    0.40
    शियन
    0.39
    Band
    0.38
    ulle
    0.38
    bent
    0.37
     అమ్మ
    0.37
     mecánica
    0.36
    和一个
    0.35
    Activations Density 0.016%

    No Known Activations