© 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. 40851
    Prev
    Next
    INDEX
    Explanations

    marcar goles y dejar huella

    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
    ربية
    0.60
    f
    0.59
     baffling
    0.54
     अधिकारियों
    0.53
    adorable
    0.53
    ודי
    0.52
     discouraging
    0.52
    bending
    0.52
     keterangan
    0.52
    दिशा
    0.52
    POSITIVE LOGITS
     ل
    0.73
     \
    0.70
     l
    0.68
     د
    0.64
    ст
    0.61
     Liu
    0.59
     Xiao
    0.59
     ن
    0.58
     I
    0.58
     CAL
    0.57
    Activations Density 0.001%

    No Known Activations