© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196410
    Prev
    Next
    INDEX
    Explanations

    new features or versions

    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_9_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
    -
    0.73
    ires
    0.65
    s
    0.63
    ীয়
    0.58
    ায়
    0.57
    ed
    0.54
    ние
    0.54
    ü
    0.54
    ிய
    0.53
    きた
    0.53
    POSITIVE LOGITS
    OMBRE
    0.70
     can
    0.68
     WITH
    0.66
     материалы
    0.66
     elucidated
    0.66
     cottonseed
    0.65
     conceito
    0.64
    ל
    0.64
    ح
    0.63
    এম
    0.63
    Activations Density 0.047%

    No Known Activations