© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28284
    Prev
    Next
    INDEX
    Explanations

    measured tone or voice

    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_10_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
    ב
    0.36
    in
    0.30
    se
    0.26
    tte
    0.25
    ll
    0.24
    ל
    0.24
    เป็น
    0.23
    tl
    0.22
    tion
    0.22
    ف
    0.21
    POSITIVE LOGITS
    ো
    0.26
    ﺌ
    0.25
     Função
    0.24
     wybra
    0.23
    Tutorial
    0.23
     criança
    0.23
     문자
    0.22
    UT
    0.22
    níci
    0.22
    RI
    0.22
    Activations Density 0.008%

    No Known Activations