© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212817
    Prev
    Next
    INDEX
    Explanations

    communicating with

    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_5_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
    یم
    1.65
    ہ
    1.60
    ス
    1.42
    ک
    1.39
    고
    1.36
    ه
    1.34
    ی
    1.31
    ά
    1.30
    ーブ
    1.30
    ナ
    1.28
    POSITIVE LOGITS
    n
    1.45
    h
    1.28
     S
    1.26
     you
    1.25
     T
    1.19
     M
    1.19
    1.19
     A
    1.18
    0
    1.17
     K
    1.13
    Activations Density 0.001%

    No Known Activations