© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106206
    Prev
    Next
    INDEX
    Explanations

    inertness

    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_1_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
    ות
    1.02
     in
    1.01
    జేపీ
    1.01
    し
    0.95
    们
    0.95
    이면
    0.86
    kým
    0.84
    ته
    0.83
    فر
    0.82
    ية
    0.81
    POSITIVE LOGITS
    ли
    1.21
    ai
    1.18
    ung
    1.06
    ana
    1.05
    it
    1.02
    ur
    1.01
    й
    1.01
    that
    1.00
    р
    1.00
    ム
    0.98
    Activations Density 0.001%

    No Known Activations