© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201582
    Prev
    Next
    INDEX
    Explanations

    that followed by descriptive verbs

    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_6_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
    ar
    1.27
    ла
    1.20
    a
    1.17
    ра
    1.10
    ่า
    1.08
    ि
    1.06
    ir
    1.05
    uk
    1.04
    ید
    1.02
    یی
    1.02
    POSITIVE LOGITS
    {
    1.14
     erreurs
    1.05
     aquifers
    1.05
     ales
    1.05
     була
    1.02
    我有
    1.01
    (
    0.98
     altri
    0.98
     waivers
    0.96
     était
    0.94
    Activations Density 0.029%

    No Known Activations