© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261083
    Prev
    Next
    INDEX
    Explanations

    create table

    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_22_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
     ప్రభ
    0.40
    HIB
    0.40
     英
    0.40
    筝
    0.40
    Needed
    0.39
     कॉम्प
    0.39
     Gespräch
    0.39
     WeChat
    0.39
     売
    0.38
    ARKS
    0.38
    POSITIVE LOGITS
     thường
    0.45
    سال
    0.41
    ica
    0.40
    емо
    0.40
     cosmet
    0.39
    meal
    0.39
     معمول
    0.38
     realities
    0.38
    ikir
    0.38
    리아
    0.38
    Activations Density 0.000%

    No Known Activations