© 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. 133628
    Prev
    Next
    INDEX
    Explanations

    Sahara Desert

    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
    ।
    1.27
     are
    1.23
     can
    1.20
     as
    1.14
     Haziran
    1.04
    to
    1.02
    .
    1.02
     she
    1.00
    ба
    1.00
    4
    0.99
    POSITIVE LOGITS
    t
    1.55
    ر
    1.14
    ز
    1.13
    िक
    1.10
    lar
    1.10
    lig
    1.10
    و
    1.07
    től
    1.06
    r
    1.06
    ையில்
    1.04
    Activations Density 0.000%

    No Known Activations