© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199494
    Prev
    Next
    INDEX
    Explanations

    special character sequences

    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
     mould
    0.40
     intre
    0.39
     exp
    0.39
     ^
    0.38
     active
    0.37
    btree
    0.36
     poate
    0.35
    acă
    0.34
    ハリ
    0.34
     bore
    0.34
    POSITIVE LOGITS
    änen
    0.42
    Multicolored
    0.42
    otechnology
    0.40
     紙
    0.40
     สมการ
    0.39
     উষ্ণ
    0.39
    Lowercase
    0.39
    ColumnKind
    0.38
    :“
    0.37
    🚺
    0.37
    Activations Density 0.000%

    No Known Activations