© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161311
    Prev
    Next
    INDEX
    Explanations

    llama ki

    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_2_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
    на
    0.88
     perils
    0.85
    า
    0.84
    т
    0.82
     are
    0.80
    ু
    0.78
    که
    0.77
    '
    0.75
     aspirated
    0.74
    лі
    0.72
    POSITIVE LOGITS
     to
    1.06
     It
    1.01
    It
    0.82
    م
    0.77
    ిన
    0.75
    ز
    0.75
    ాలు
    0.73
    jších
    0.71
    ER
    0.70
    I
    0.70
    Activations Density 0.000%

    No Known Activations