© 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. 112041
    Prev
    Next
    INDEX
    Explanations

    strengths

    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
    ларга
    1.28
    ۹
    1.26
    ться
    1.18
    with
    1.16
    ل
    1.09
    न्दावन
    1.08
    ių
    1.03
    ᓘ
    1.03
    alama
    1.02
    ेंगू
    1.00
    POSITIVE LOGITS
    م
    1.29
     at
    1.26
    س
    1.16
    {
    1.10
    ER
    1.04
     但
    1.02
    ના
    0.99
    }\
    0.98
     ersten
    0.94
     konnte
    0.94
    Activations Density 0.004%

    No Known Activations