© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39434
    Prev
    Next
    INDEX
    Explanations

    As you know,

    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_3_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
    s
    0.74
     new
    0.65
     exposé
    0.63
     पीड़ित
    0.63
     intrat
    0.62
     taboo
    0.61
    tainment
    0.60
     खिलाड़ी
    0.59
     attain
    0.59
     fuzzy
    0.58
    POSITIVE LOGITS
    ة
    0.70
    ות
    0.68
    IN
    0.68
     Verlauf
    0.66
    ي
    0.66
    ца
    0.65
    ми
    0.64
     Executes
    0.63
    u
    0.62
    at
    0.61
    Activations Density 0.008%

    No Known Activations