© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81478
    Prev
    Next
    INDEX
    Explanations

    Bahamas, pajamas

    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_0_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
     decentral
    1.18
    几
    1.13
    ності
    1.11
    ர்ஸ்
    1.09
     for
    1.08
     നിന്ന്
    1.08
    یی
    1.03
     اٹھ
    1.01
    迌
    0.98
    憚
    0.98
    POSITIVE LOGITS
    a
    1.91
    ↵
    1.83
    m
    1.60
    া
    1.58
    u
    1.53
    ס
    1.52
    ai
    1.51
    et
    1.49
    o
    1.48
    á
    1.46
    Activations Density 0.000%

    No Known Activations