© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119261
    Prev
    Next
    INDEX
    Explanations

    software names and technologies

    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_27_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
    banners
    0.36
    Appending
    0.35
    ្ស
    0.33
    ,''
    0.32
    lestage
    0.32
    sbParams
    0.31
     penelitian
    0.31
    ଯ
    0.31
     dhamme
    0.30
    appending
    0.30
    POSITIVE LOGITS
     Agr
    0.38
     clearly
    0.38
     Clearly
    0.36
     turn
    0.36
     Swift
    0.35
     {:
    0.35
     Matters
    0.35
     Initialization
    0.35
     Runde
    0.35
     Introduction
    0.34
    Activations Density 0.017%

    No Known Activations