© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138411
    Prev
    Next
    INDEX
    Explanations

    fantasy sports

    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_37_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
     пос
    0.39
     पस
    0.38
    ክ
    0.35
    CRIPTION
    0.35
     naveg
    0.34
    钲
    0.34
    țit
    0.34
     Herd
    0.33
    徹
    0.33
     cere
    0.33
    POSITIVE LOGITS
     fantasy
    1.99
     Fantasy
    1.83
    Fantasy
    1.78
    fantasy
    1.74
     fantasies
    1.47
     fantas
    1.37
     фанта
    1.32
     Fant
    1.21
     fantasia
    1.21
     fant
    1.18
    Activations Density 0.001%

    No Known Activations