© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13417
    Prev
    Next
    INDEX
    Explanations

    infinity and addWidget

    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_13_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
     время
    0.19
    AddTime
    0.18
    К
    0.18
     ajoute
    0.17
     বলছে
    0.17
     لك
    0.16
     전쟁
    0.16
     rues
    0.16
    вная
    0.16
     cuốn
    0.15
    POSITIVE LOGITS
    t
    0.19
    `.
    0.17
    figsize
    0.16
    镜头
    0.16
     preh
    0.16
    hepat
    0.16
    asys
    0.16
    as
    0.15
    beqz
    0.15
    veyor
    0.14
    Activations Density 0.003%

    No Known Activations