© 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. 260501
    Prev
    Next
    INDEX
    Explanations

    think about it

    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_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
    usuario
    0.45
    DOM
    0.43
    ratie
    0.40
    ﺵ
    0.40
    rectangle
    0.39
     உதாரணமாக
    0.38
     (’
    0.38
     okresie
    0.38
    Scr
    0.37
    عار
    0.37
    POSITIVE LOGITS
    ട്ടില്ല
    0.45
     специально
    0.41
     tesam
    0.39
     beforePath
    0.39
     Onion
    0.39
     городской
    0.38
    tego
    0.38
    栤
    0.38
    FreeBuf
    0.38
     ইস্ট
    0.37
    Activations Density 0.000%

    No Known Activations