© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4546
    Prev
    Next
    INDEX
    Explanations

    out_channels and assignment

    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_39_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
    annter
    0.40
    礡
    0.39
     sculptural
    0.38
     Seda
    0.38
    ᠶ
    0.37
     Đế
    0.36
    okus
    0.36
     طراحی
    0.36
    摂取
    0.35
    ালার
    0.34
    POSITIVE LOGITS
    &
    0.40
    perform
    0.40
    Coord
    0.39
     Perform
    0.38
     выход
    0.37
     coordinating
    0.36
    &\
    0.35
     Gifts
    0.35
     Coordinating
    0.35
     perform
    0.35
    Activations Density 0.000%

    No Known Activations