© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134547
    Prev
    Next
    INDEX
    Explanations

    TabSynDex, TechRadar, Edison, Tabacchi, Tabula Rasa

    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
    I
    1.34
    als
    1.02
    O
    1.02
    Q
    1.02
    ators
    1.00
    ating
    0.98
    ening
    0.96
    A
    0.96
    ،
    0.94
    OR
    0.93
    POSITIVE LOGITS
    리
    1.38
    生活
    1.32
    可
    1.24
    について
    1.21
    特
    1.21
    利
    1.20
    타
    1.20
    多
    1.17
    스
    1.17
     ciudad
    1.16
    Activations Density 0.024%

    No Known Activations