© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195451
    Prev
    Next
    INDEX
    Explanations

    liberation, evolution, or Oeridian

    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_4_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
    3
    1.42
    大
    1.38
    2
    1.36
    é
    0.99
    ある
    0.97
    ă
    0.96
    ३
    0.95
    ä
    0.93
    1
    0.92
    the
    0.89
    POSITIVE LOGITS
     in
    1.41
    ও
    1.05
    ম
    0.98
    も
    0.95
     drugih
    0.88
    ضای
    0.85
    ิน
    0.82
    <0x80>
    0.80
     it
    0.79
     şirket
    0.79
    Activations Density 0.004%

    No Known Activations