© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41630
    Prev
    Next
    INDEX
    Explanations

    **E**xponents / **O**rders

    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_22_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
     unrecognizable
    0.25
     localObject
    0.24
     elektry
    0.24
    বীন্দ্রনাথ
    0.23
     regering
    0.23
     obstructing
    0.23
     electricidad
    0.23
    𝚄
    0.23
     lepro
    0.22
     mangroves
    0.22
    POSITIVE LOGITS
    stat
    0.21
    ↵
    0.20
     Use
    0.20
    包括
    0.20
    los
    0.19
    as
    0.19
    ad
    0.19
    可
    0.19
    use
    0.19
    ianas
    0.19
    Activations Density 0.006%

    No Known Activations