© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209358
    Prev
    Next
    INDEX
    Explanations

    wanted persons or posters

    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_10_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
    و
    0.23
    _
    0.23
    ್ರಾ
    0.21
    mith
    0.21
     एवं
    0.20
    ربي
    0.20
    manufacturer
    0.20
     ដោយ
    0.20
     โดย
    0.19
    worthiness
    0.19
    POSITIVE LOGITS
    রিদ্র
    0.21
    k
    0.19
    h
    0.19
    し
    0.18
    ４
    0.18
    kts
    0.18
    써
    0.18
    c
    0.17
    cı
    0.17
    ad
    0.17
    Activations Density 0.001%

    No Known Activations