© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50688
    Prev
    Next
    INDEX
    Explanations

    Varies

    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
    দের
    0.45
    A
    0.45
    '
    0.43
    O
    0.39
     Ев
    0.39
    P
    0.38
    U
    0.38
    T
    0.38
    OS
    0.36
    S
    0.36
    POSITIVE LOGITS
    ivät
    0.42
     développ
    0.38
     behö
    0.37
     rekao
    0.35
    itet
    0.35
     quotations
    0.35
    ală
    0.34
     HttpClient
    0.33
     specif
    0.33
    ری
    0.33
    Activations Density 0.013%

    No Known Activations