© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54498
    Prev
    Next
    INDEX
    Explanations

    UTF-8 encoding

    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_30_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
    陽
    0.40
     ಗ್ರಾ
    0.37
    initpos
    0.36
     удалось
    0.36
     دھ
    0.36
     পার্শ্ব
    0.36
    нные
    0.36
     ILLINOIS
    0.35
    ˬ
    0.35
     lunghezza
    0.35
    POSITIVE LOGITS
     realization
    0.38
     ఇం
    0.37
     Knows
    0.37
     optimization
    0.36
    呈现
    0.36
    говор
    0.35
    的设计
    0.35
     Pines
    0.34
     ERR
    0.34
     Injection
    0.34
    Activations Density 0.000%

    No Known Activations