© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162074
    Prev
    Next
    INDEX
    Explanations

    service and sourcing

    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_31_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
    ၆
    0.40
     maximale
    0.37
     characteristic
    0.36
    storeItem
    0.36
     quarterback
    0.36
    箇所
    0.36
     GitHub
    0.36
     criterion
    0.35
     фильмы
    0.35
     alopecia
    0.35
    POSITIVE LOGITS
    AC
    0.34
     SMART
    0.33
    庞
    0.32
     располага
    0.31
    บวน
    0.31
    ChooserView
    0.31
     ABC
    0.31
    জন্ম
    0.30
    Reach
    0.30
     رف
    0.30
    Activations Density 0.013%

    No Known Activations