© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60763
    Prev
    Next
    INDEX
    Explanations

    Ren Amamiya, René, Renju, Renjiro

    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_2_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
    н
    0.98
    م
    0.96
    ita
    0.81
    ۔
    0.77
    м
    0.76
    。
    0.74
    你
    0.70
    is
    0.66
    ר
    0.64
     by
    0.64
    POSITIVE LOGITS
    t
    1.07
    től
    0.98
    ุ
    0.96
    ्स
    0.90
    tiden
    0.82
    temperatur
    0.82
    typen
    0.80
    ttt
    0.77
    top
    0.75
    tional
    0.75
    Activations Density 0.000%

    No Known Activations