© 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. 220940
    Prev
    Next
    INDEX
    Explanations

    counting objects with multiple legs

    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
     Tunisie
    0.41
     Tunisian
    0.40
     Tunisia
    0.39
     hoo
    0.38
     قیام
    0.38
     +#
    0.37
     revolt
    0.37
     Belly
    0.37
    枺
    0.37
     belly
    0.37
    POSITIVE LOGITS
    Vertical
    0.40
    Peter
    0.40
    Forg
    0.36
     Peter
    0.35
     हथ
    0.35
    Posture
    0.34
    Diagnostics
    0.34
     Jai
    0.34
    Frames
    0.34
     Redskins
    0.34
    Activations Density 0.001%

    No Known Activations