© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24506
    Prev
    Next
    INDEX
    Explanations

    tiptoeing around / toe nailing

    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_10_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
     dicht
    0.66
     setzen
    0.62
     schaffen
    0.61
     endorph
    0.55
     setzt
    0.55
     pedestrians
    0.54
     erricht
    0.54
    ت
    0.54
     pedestrian
    0.54
     niedrig
    0.53
    POSITIVE LOGITS
     Ле
    0.53
    nueva
    0.48
    子の
    0.48
     Jeżeli
    0.46
    vä
    0.45
    vors
    0.45
    மெ
    0.45
    margins
    0.45
    Methyl
    0.44
    ڠ
    0.44
    Activations Density 0.017%

    No Known Activations