© 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. 35482
    Prev
    Next
    INDEX
    Explanations

    By + 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_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
    ᱕
    0.60
    endment
    0.57
    9
    0.57
     Hälfte
    0.56
    ᱗
    0.56
    yi
    0.55
     Huber
    0.55
     FIXME
    0.55
    SPECT
    0.54
    ᒐ
    0.53
    POSITIVE LOGITS
    可以说是
    0.61
     这
    0.56
    вала
    0.56
    constraintTop
    0.54
    вался
    0.54
     سبق
    0.52
    то
    0.51
    配送
    0.51
    舒服
    0.51
     descoberta
    0.50
    Activations Density 0.003%

    No Known Activations