© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130406
    Prev
    Next
    INDEX
    Explanations

    вета, ке

    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_1_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
    е
    1.51
    ї
    1.30
    ני
    1.29
     dolayı
    1.27
    и
    1.24
    arı
    1.22
    .
    1.22
    jší
    1.15
    а
    1.14
    .?
    1.09
    POSITIVE LOGITS
    u
    1.20
    وأ
    1.05
     is
    1.03
    وية
    1.03
    న
    1.02
    ط
    1.00
    ويل
    0.96
    og
    0.88
    ných
    0.84
     (
    0.82
    Activations Density 0.000%

    No Known Activations