© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147799
    Prev
    Next
    INDEX
    Explanations

    troubleshooting steps or product details

    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_18_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
     Trabal
    0.51
     worksheets
    0.50
     Рабо
    0.46
    )</
    0.44
     ойной
    0.44
    kills
    0.42
     ऑफलाइन
    0.41
     kills
    0.41
     কর্মসূ
    0.40
     сидя
    0.40
    POSITIVE LOGITS
    neyland
    0.46
     HUAWEI
    0.45
    voit
    0.44
     preamp
    0.44
    MIDI
    0.44
     längre
    0.43
    ﺶ
    0.43
    Despatx
    0.43
    ኻ
    0.43
     parl
    0.42
    Activations Density 0.022%

    No Known Activations