© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39528
    Prev
    Next
    INDEX
    Explanations

    automation commands

    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_11_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
    ضافة
    0.55
    up
    0.55
     buying
    0.52
     Buying
    0.51
    -
    0.50
     teeming
    0.50
     “
    0.49
     Brands
    0.49
    geb
    0.49
    :
    0.49
    POSITIVE LOGITS
    r
    0.61
    BOOLE
    0.59
    ר
    0.59
     audioEngine
    0.56
    unkt
    0.55
    رير
    0.55
    RENDITION
    0.55
    determine
    0.54
    getSize
    0.54
    Ꮞ
    0.54
    Activations Density 0.007%

    No Known Activations