© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30611
    Prev
    Next
    INDEX
    Explanations

    modelits/the/a behavior, quality, number

    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_7_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
     tutkim
    0.46
    ی
    0.42
     sows
    0.41
    ༞
    0.38
    ন্যায়
    0.37
    कीस
    0.37
     मिरची
    0.37
    EY
    0.36
    ิค
    0.36
     stenosis
    0.36
    POSITIVE LOGITS
    -
    0.55
    ↵↵
    0.52
    on
    0.52
    an
    0.52
    ad
    0.51
     (
    0.50
    in
    0.50
    r
    0.50
    er
    0.50
    st
    0.48
    Activations Density 0.027%

    No Known Activations