© 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. 90493
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     proš
    0.60
     přek
    0.54
     πρόσ
    0.52
    φό
    0.50
    žem
    0.50
    ă
    0.50
     beschikbaar
    0.50
    isons
    0.50
    šće
    0.50
     доступ
    0.49
    POSITIVE LOGITS
    தின
    0.61
    मय
    0.58
    ﺘ
    0.58
    Michigan
    0.56
     Michigan
    0.55
    лит
    0.55
    naming
    0.55
    "。
    0.54
    testid
    0.54
    }}"
    0.53
    Activations Density 0.001%

    No Known Activations