© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 382
    Prev
    Next
    INDEX
    Explanations

    declaration mechanisms and styles

    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_40_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
     nonradiative
    0.39
    undaria
    0.36
    讨
    0.36
    ্থ
    0.36
     reductive
    0.35
    ibles
    0.35
    ivores
    0.35
     imperfect
    0.34
     सैल
    0.34
     সেল
    0.34
    POSITIVE LOGITS
     minded
    0.41
    =!
    0.39
    하게
    0.37
    ζα
    0.36
     Ratt
    0.35
    Rock
    0.35
    ALLY
    0.34
    Pou
    0.34
    ☚
    0.34
     вс
    0.34
    Activations Density 0.243%

    No Known Activations