© 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. 206365
    Prev
    Next
    INDEX
    Explanations

    resistance levels

    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
     毛
    0.46
     வங்கி
    0.46
     شناس
    0.44
    ționale
    0.44
    共产党
    0.44
     க
    0.43
     खिलाड़ियों
    0.43
     Japanese
    0.43
     хими
    0.42
     পরিচয়
    0.42
    POSITIVE LOGITS
    वायु
    0.47
     subd
    0.43
    캄
    0.41
    antiene
    0.41
    ঈ
    0.41
     infil
    0.40
     شم
    0.40
     O
    0.40
    ghi
    0.40
     metaf
    0.39
    Activations Density 0.000%

    No Known Activations