© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86040
    Prev
    Next
    INDEX
    Explanations

    exhale slowly

    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_23_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
     సమయంలో
    0.23
    Brazilian
    0.22
     suivant
    0.22
     folgenden
    0.21
     बराम
    0.21
    次の
    0.20
    ہیں
    0.20
    鲲
    0.20
     ملے
    0.20
    মনের
    0.20
    POSITIVE LOGITS
    Clos
    0.24
    sharp
    0.21
    clos
    0.20
     mod
    0.20
     takt
    0.20
     ക്
    0.19
     koop
    0.19
    fit
    0.19
     อีก
    0.19
    keit
    0.19
    Activations Density 0.001%

    No Known Activations