© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59245
    Prev
    Next
    INDEX
    Explanations

    failure

    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
    ت
    0.73
    תן
    0.68
     diat
    0.59
    ת
    0.59
     carapace
    0.57
    escape
    0.57
     composure
    0.57
    ইয়া
    0.57
    lık
    0.56
    hana
    0.56
    POSITIVE LOGITS
     aby
    0.66
     echter
    0.66
    ッ
    0.63
     presente
    0.60
     sommet
    0.60
     onderdeel
    0.60
     原因
    0.59
     Critical
    0.57
     Base
    0.57
     新
    0.57
    Activations Density 0.013%

    No Known Activations