© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124917
    Prev
    Next
    INDEX
    Explanations

    flammability, flayer, flirty, flagon, flushes, fläming

    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_3_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
    دی
    1.00
    ва
    1.00
    ור
    0.98
    ى
    0.96
    S
    0.94
    ید
    0.94
    い
    0.91
    ла
    0.90
     अभिनय
    0.88
    ा
    0.86
    POSITIVE LOGITS
    0
    1.10
    t
    1.01
    ER
    0.96
    the
    0.85
    The
    0.82
    s
    0.82
    d
    0.81
     for
    0.80
    l
    0.77
    ARE
    0.74
    Activations Density 0.000%

    No Known Activations