© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167085
    Prev
    Next
    INDEX
    Explanations

    hiking and walking tours

    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
    threshold
    0.38
    instagram
    0.37
     صحيح
    0.35
    PAGE
    0.35
     threshold
    0.34
    pinterest
    0.34
    뀌
    0.34
    ੧
    0.34
     ಹೋಗ
    0.34
    ífer
    0.34
    POSITIVE LOGITS
     ovale
    0.43
     Lies
    0.40
    তির
    0.38
     café
    0.38
    льзу
    0.37
    хия
    0.36
     Pred
    0.36
     cafés
    0.36
    鍍
    0.36
     negócio
    0.35
    Activations Density 0.002%

    No Known Activations