© 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. 38475
    Prev
    Next
    INDEX
    Explanations

    Zorn's Lemma, Eclipse

    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
    的三
    0.65
    rí
    0.62
     SUBSTITUTE
    0.60
    είου
    0.59
     fluctuate
    0.59
    
    0.59
     sluč
    0.58
    vés
    0.58
    筮
    0.57
    databinding
    0.57
    POSITIVE LOGITS
     on
    0.84
    </b>
    0.68
     आय
    0.62
    (
    0.57
    US
    0.57
    AT
    0.57
    V
    0.57
    IC
    0.56
    art
    0.55
    ong
    0.55
    Activations Density 0.005%

    No Known Activations