© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203971
    Prev
    Next
    INDEX
    Explanations

    Roh/Rho

    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
     ग
    0.47
     ========
    0.42
     ignition
    0.38
    Apellido
    0.37
    ato
    0.37
    atação
    0.37
     个
    0.36
     ગ
    0.36
    馴
    0.35
    ссо
    0.35
    POSITIVE LOGITS
    rH
    0.42
     ფორ
    0.40
    der
    0.38
    Duong
    0.38
    Tram
    0.37
    defl
    0.37
    covers
    0.37
     roh
    0.37
     кур
    0.37
    ῆ
    0.37
    Activations Density 0.000%

    No Known Activations