© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157428
    Prev
    Next
    INDEX
    Explanations

    Indonesian and Spanish phrases

    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
    ۔
    1.20
    ত
    0.97
    ค
    0.93
    ޟ
    0.92
    ’
    0.91
    ן
    0.90
     disabilities
    0.87
    0.86
    ক
    0.86
    のもの
    0.84
    POSITIVE LOGITS
    ale
    1.26
    2
    1.26
    ل
    1.23
    ని
    1.16
    ных
    1.15
    ك
    1.11
    ного
    1.10
    ent
    1.09
    ick
    1.09
     segunda
    1.05
    Activations Density 0.000%

    No Known Activations