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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129627
    Prev
    Next
    INDEX
    Explanations

    in our case

    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_25_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
     developmental
    0.43
     Developmental
    0.41
    ografica
    0.40
     eenvoud
    0.40
    迩
    0.40
    িয়
    0.38
    مع
    0.38
    峼
    0.38
    मैंने
    0.38
     الى
    0.36
    POSITIVE LOGITS
    '));
    0.46
     drain
    0.41
    ']);
    0.38
     dlatego
    0.37
     slice
    0.37
     پھیل
    0.36
    "));
    0.36
     tepi
    0.35
    ');
    0.35
     flap
    0.35
    Activations Density 0.006%

    No Known Activations