© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62016
    Prev
    Next
    INDEX
    Explanations

    pop, pp, ppp, popular, poppopopoo, Popplio

    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_2_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
    و
    1.29
    ب
    1.18
    م
    1.14
    ాలు
    1.11
    ான
    1.10
    넬
    1.05
    지
    1.05
    ו
    1.04
    یده
    1.03
     μία
    1.03
    POSITIVE LOGITS
     I
    1.43
     A
    1.41
    a
    1.34
     a
    1.20
    1
    1.18
     K
    1.17
     ৮
    1.16
    h
    1.14
    8
    1.11
     B
    1.09
    Activations Density 0.001%

    No Known Activations