© 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. 76519
    Prev
    Next
    INDEX
    Explanations

    hockey game positions

    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
     puck
    0.62
     Hockey
    0.60
     NHL
    0.59
     hockey
    0.58
    🏒
    0.54
    Hockey
    0.51
    hockey
    0.50
     Puck
    0.46
    NHL
    0.45
     Stanley
    0.44
    POSITIVE LOGITS
    谅
    0.39
     pensamiento
    0.37
     औसत
    0.37
     lluvias
    0.35
    MyDrive
    0.35
    evoluzione
    0.35
    ഭ്യാസ
    0.34
     ayudas
    0.34
     libertà
    0.34
    BooleanField
    0.34
    Activations Density 0.000%

    No Known Activations