© 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. 34887
    Prev
    Next
    INDEX
    Explanations

    programming, language, and cultural terms

    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
     trái
    0.39
     براہ
    0.36
     बचाव
    0.36
     जिंदा
    0.36
     sawtooth
    0.35
    okin
    0.35
     можли
    0.35
     *}(
    0.35
     خداوند
    0.34
    BTS
    0.34
    POSITIVE LOGITS
     usefulness
    0.40
    luence
    0.39
    夥伴
    0.39
     Treas
    0.36
     structure
    0.36
    ரச
    0.36
    structure
    0.36
    vari
    0.35
    erful
    0.35
     struttura
    0.35
    Activations Density 0.004%

    No Known Activations