© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35950
    Prev
    Next
    INDEX
    Explanations

    general knowledge and purposes

    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_11_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
     Ս
    0.36
    ン
    0.35
    पीएफ
    0.35
    ﺪ
    0.34
     Điện
    0.33
    Clothes
    0.33
    ﺮ
    0.33
    郃
    0.33
    𒀭
    0.32
    IDTH
    0.32
    POSITIVE LOGITS
    from
    0.40
    จาก
    0.36
    are
    0.35
    {
    0.30
    '
    0.30
    0.30
    \(
    0.29
    http
    0.29
    with
    0.29
     από
    0.28
    Activations Density 0.010%

    No Known Activations