© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    effects and conditions

    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
    Ϯ
    0.28
    ‌,
    0.28
    ре
    0.27
    ی
    0.27
    ফে
    0.26
    溶液
    0.26
    en
    0.25
     titrated
    0.25
    YT
    0.25
    ता
    0.25
    POSITIVE LOGITS
    ó
    0.25
    ión
    0.24
    istä
    0.24
     põ
    0.24
     específicas
    0.24
    ziel
    0.23
    gea
    0.23
     jährlich
    0.23
    íst
    0.22
     válida
    0.22
    Activations Density 0.123%

    No Known Activations