© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260318
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     a
    0.54
     upkeep
    0.54
     dicen
    0.47
     tierra
    0.47
     چاہیے۔
    0.46
    훨
    0.46
    кро
    0.45
     مقدار
    0.45
    iven
    0.44
     ویت
    0.44
    POSITIVE LOGITS
    D
    0.45
     осве
    0.42
     identifiers
    0.41
    dagen
    0.41
    ³,
    0.41
     fingern
    0.40
     الاطلاع
    0.40
     analogies
    0.39
    离婚
    0.39
     entstanden
    0.38
    Activations Density 0.000%

    No Known Activations