© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46721
    Prev
    Next
    INDEX
    Explanations

    spatial extent and scale

    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_13_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
    㪇
    0.38
    </h3>
    0.35
     ბ
    0.35
    )”.
    0.34
     произо
    0.33
    ratto
    0.33
    )”
    0.33
     dalších
    0.33
    ძ
    0.32
    䛺
    0.32
    POSITIVE LOGITS
    Kale
    0.31
     Kale
    0.30
    ﻂ
    0.29
     Kadar
    0.29
     forested
    0.28
     eyeb
    0.28
     scaled
    0.28
     Hastings
    0.28
     spider
    0.27
    зму
    0.27
    Activations Density 0.046%

    No Known Activations