© 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. 2536
    Prev
    Next
    INDEX
    Explanations

    a little more

    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
    Jade
    0.36
    aughan
    0.35
    يرين
    0.34
     cómodo
    0.33
    Yvette
    0.33
    ラク
    0.32
     بول
    0.32
    줄
    0.31
    괄
    0.31
    玉
    0.31
    POSITIVE LOGITS
     phenomena
    0.37
     ceremony
    0.36
     recid
    0.35
     немно
    0.34
     publisher
    0.33
     MPG
    0.33
     psych
    0.33
     psychopath
    0.33
    해야
    0.32
    𝚙
    0.32
    Activations Density 0.063%

    No Known Activations