© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236573
    Prev
    Next
    INDEX
    Explanations

    mastering skills or topics

    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_25_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
     buddhav
    0.44
    goài
    0.38
    מונה
    0.38
    ילו
    0.37
    reflectionCamera
    0.37
    用い
    0.37
     ▸
    0.36
     ממ
    0.36
     전에
    0.35
    婍
    0.35
    POSITIVE LOGITS
     Labs
    0.41
     kinerja
    0.39
    мед
    0.39
    Sleep
    0.39
    kart
    0.39
     bar
    0.38
    knowledge
    0.38
    bar
    0.38
     Sleep
    0.38
    лог
    0.38
    Activations Density 0.002%

    No Known Activations