© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196246
    Prev
    Next
    INDEX
    Explanations

    often '*' or numbers

    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_26_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
    u
    0.24
    ه
    0.22
    ת
    0.21
    و
    0.20
    ع
    0.19
    in
    0.19
    an
    0.19
    on
    0.18
    на
    0.18
    علم
    0.18
    POSITIVE LOGITS
     परिजनों
    0.18
    SubDirectory
    0.18
    alarına
    0.17
    िशनर
    0.17
     figurine
    0.17
     परिजन
    0.17
    FileURL
    0.16
    वृत्ति
    0.16
    ether
    0.16
    
    0.16
    Activations Density 0.002%

    No Known Activations