© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82625
    Prev
    Next
    INDEX
    Explanations

    species

    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_0_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
     entend
    1.31
     diminu
    1.28
    padă
    1.27
     estamp
    1.26
    둰
    1.26
     amélior
    1.25
     ομά
    1.24
     assin
    1.24
     tarses
    1.23
     mouve
    1.22
    POSITIVE LOGITS
    ing
    1.87
    at
    1.73
    ة
    1.56
    一
    1.46
    in
    1.42
    5
    1.42
    2
    1.38
    </h2>
    1.36
     (
    1.21
    inin
    1.19
    Activations Density 0.002%

    No Known Activations