© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52602
    Prev
    Next
    INDEX
    Explanations

    not a simple

    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
     الْم
    0.42
     RE
    0.39
     консу
    0.38
     thậm
    0.38
     А
    0.38
    уса
    0.37
     Engine
    0.35
    ที่สุด
    0.35
    黨
    0.35
    ﺜ
    0.35
    POSITIVE LOGITS
    èques
    0.41
    ":
    0.40
    ior
    0.39
    other
    0.39
     নিঃস
    0.38
    Other
    0.37
    Where
    0.37
     ಇತರ
    0.37
    YER
    0.37
    astos
    0.36
    Activations Density 0.020%

    No Known Activations