© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211141
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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_20_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
    ঠ
    0.38
     riv
    0.32
    兼
    0.32
    ій
    0.32
    らせ
    0.31
     توان
    0.31
    怡
    0.31
     ОО
    0.31
    垂
    0.31
     அள
    0.30
    POSITIVE LOGITS
     jugar
    0.40
    '){
    0.38
     प्यार
    0.35
    arah
    0.35
    }$
    0.34
     ellipsis
    0.34
     unjustly
    0.34
    ');
    0.34
     escritor
    0.33
     guerras
    0.33
    Activations Density 0.000%

    No Known Activations