© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89648
    Prev
    Next
    INDEX
    Explanations

    gastrointestinal tract, Impact

    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_3_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
    ﻟ
    0.87
    ה
    0.80
    oną
    0.76
     quản
    0.73
     distraught
    0.73
    șt
    0.72
    ه
    0.70
    ții
    0.69
     إذا
    0.68
     смесь
    0.68
    POSITIVE LOGITS
    de
    0.68
     Bevan
    0.59
     Namen
    0.57
    Novo
    0.57
    op
    0.56
    瑗
    0.56
    ება
    0.55
     operativos
    0.55
    opre
    0.55
     epoca
    0.54
    Activations Density 0.000%

    No Known Activations