© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196786
    Prev
    Next
    INDEX
    Explanations

    names and literary characters

    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_15_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
    ości
    0.57
    ğimiz
    0.56
    urbo
    0.54
    া
    0.52
     Frazier
    0.52
     ínt
    0.50
    essai
    0.50
    afstand
    0.49
    oud
    0.49
    ológico
    0.48
    POSITIVE LOGITS
     قالت
    0.58
     କ
    0.57
     бюджет
    0.54
    公演
    0.54
     huyện
    0.53
     hạn
    0.53
     hunt
    0.51
    健康的
    0.51
     Ж
    0.51
    IRONMENT
    0.51
    Activations Density 0.000%

    No Known Activations