© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202518
    Prev
    Next
    INDEX
    Explanations

    Surface area to volume ratio

    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_12_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
    I
    0.17
     mathvariant
    0.15
    Area
    0.14
    范围
    0.14
    .”
    0.14
    .
    0.14
     hém
    0.13
    <
    0.13
    场
    0.13
    Bottom
    0.13
    POSITIVE LOGITS
     MILLER
    0.16
     HERO
    0.15
     RAT
    0.15
     probative
    0.15
     glaring
    0.14
     ಕಾರಣ
    0.14
     crystallized
    0.14
     tenuous
    0.14
    presentableId
    0.14
    ਟੀ
    0.14
    Activations Density 0.001%

    No Known Activations