© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61635
    Prev
    Next
    INDEX
    Explanations

    long time

    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_11_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
     Roasted
    0.60
     captain
    0.54
     EXECUTIVE
    0.53
     Thanksgiving
    0.52
     executive
    0.52
     ssid
    0.52
    흘
    0.51
    忔
    0.51
     Oh
    0.50
     touched
    0.50
    POSITIVE LOGITS
    CTest
    0.61
    力度
    0.57
    댕
    0.57
    www
    0.56
    preco
    0.55
    hame
    0.54
     społec
    0.54
    śmy
    0.54
    пресс
    0.52
    alura
    0.52
    Activations Density 0.000%

    No Known Activations