© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6720
    Prev
    Next
    INDEX
    Explanations

    App DbContext

    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
     Tjiwarl
    0.42
    奘
    0.41
    孅
    0.39
    ᓴ
    0.39
    REGIUNE
    0.38
    စိတ်
    0.38
    挕
    0.38
    tDBOutput
    0.38
    ᒥ
    0.38
    𒁀
    0.37
    POSITIVE LOGITS
     main
    0.40
     p
    0.39
    0.37
     c
    0.35
    0
    0.35
     runs
    0.34
     multi
    0.34
     target
    0.33
     P
    0.33
     run
    0.33
    Activations Density 0.059%

    No Known Activations