© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77879
    Prev
    Next
    INDEX
    Explanations

    English to other language translations

    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_29_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
     ઇ
    0.47
     Piso
    0.45
     Hrvatskoj
    0.43
    رمز
    0.42
    धारा
    0.41
    鍱
    0.40
     нер
    0.40
     பொருளாதார
    0.40
     Grail
    0.40
     LUMPUR
    0.40
    POSITIVE LOGITS
    जिसे
    0.40
    ]]
    0.38
    れている
    0.38
    วัส
    0.37
    ]`
    0.37
     noter
    0.36
     permits
    0.36
    gy
    0.35
     denial
    0.35
    込
    0.35
    Activations Density 0.003%

    No Known Activations