© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76904
    Prev
    Next
    INDEX
    Explanations

    horse, horsepower, mule

    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_31_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
    meisterschaft
    0.38
     acte
    0.37
     Anastasia
    0.36
     typeface
    0.36
    {}
    0.35
     nomina
    0.35
    comics
    0.35
    Anast
    0.35
     చర్య
    0.35
     meubles
    0.35
    POSITIVE LOGITS
     mule
    0.48
     horsepower
    0.46
     horse
    0.45
     mules
    0.44
    骡
    0.42
    Horse
    0.42
     horses
    0.42
    horsepower
    0.40
     stallions
    0.39
     Horses
    0.38
    Activations Density 0.060%

    No Known Activations