© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199711
    Prev
    Next
    INDEX
    Explanations

    habits and routines

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    वळ
    0.40
    页面存档备份
    0.40
     Sle
    0.39
    ="{{
    0.38
     Sly
    0.38
    ায়ী
    0.37
    Hosted
    0.37
    itz
    0.36
     dedicada
    0.36
    म्मी
    0.35
    POSITIVE LOGITS
    논
    0.41
    ENTES
    0.38
    agona
    0.38
    ነስ
    0.36
    举
    0.36
    蓼
    0.36
     논
    0.36
     raised
    0.34
    Raising
    0.34
    양
    0.34
    Activations Density 0.001%

    No Known Activations