© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4440
    Prev
    Next
    INDEX
    Explanations

    json indent =

    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_39_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
     เก็
    0.33
     配置
    0.33
    InstanceManager
    0.32
     वैश्विक
    0.32
     دیں
    0.31
     န
    0.29
    桥
    0.29
     खरेदी
    0.29
     समीकरण
    0.29
     epidemiology
    0.29
    POSITIVE LOGITS
    vação
    0.35
    elung
    0.31
    mediation
    0.30
    packed
    0.28
    !),
    0.28
     Gw
    0.28
     Divinity
    0.28
    ጃ
    0.27
    minsize
    0.27
    styles
    0.26
    Activations Density 0.026%

    No Known Activations