© 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. 198888
    Prev
    Next
    INDEX
    Explanations

    drop

    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
     jaune
    0.36
     baku
    0.36
    萛
    0.36
     ван
    0.36
    Facet
    0.36
    ான்
    0.35
    cose
    0.35
    ุก
    0.34
    чета
    0.34
     Ад
    0.34
    POSITIVE LOGITS
     Off
    0.42
    TOOLS
    0.39
     off
    0.38
    <unused0>
    0.38
     поки
    0.38
    aparikkh
    0.37
    आईआर
    0.37
    ৈ
    0.37
     কিলো
    0.37
    راک
    0.36
    Activations Density 0.002%

    No Known Activations