© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32939
    Prev
    Next
    INDEX
    Explanations

    say ):

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     लिरिक्स
    0.38
     Thereafter
    0.36
    вање
    0.35
    峈
    0.35
    枒
    0.34
    aughey
    0.33
    வையாக
    0.33
    પ
    0.32
    Lisa
    0.32
     Wouldn
    0.32
    POSITIVE LOGITS
     modeled
    0.45
     -
    0.40
     alleg
    0.36
    ")
    0.36
     modeling
    0.36
     –
    0.36
     devol
    0.35
     edible
    0.35
     nut
    0.35
     art
    0.35
    Activations Density 0.013%

    No Known Activations