© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90252
    Prev
    Next
    INDEX
    Explanations

    iPadOS

    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_3_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
    ك
    0.71
    }");
    0.69
     офис
    0.66
     başlang
    0.65
     байланы
    0.64
    }";
    0.64
    𝐝
    0.64
     gắng
    0.64
     вино
    0.60
     каждое
    0.60
    POSITIVE LOGITS
    it
    1.00
    ي
    0.85
    i
    0.83
    ing
    0.80
    에
    0.76
    itl
    0.72
    í
    0.72
    ة
    0.69
    o
    0.68
    ij
    0.67
    Activations Density 0.005%

    No Known Activations