© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19384
    Prev
    Next
    INDEX
    Explanations

    la brea / ice age

    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_15_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
    ئي
    0.63
     fürs
    0.59
     ′
    0.55
     vicepresidente
    0.54
    स्ट
    0.54
    िल्‍ली
    0.53
     für
    0.51
     उपाध्यक्ष
    0.51
     *)$
    0.51
     exiled
    0.51
    POSITIVE LOGITS
     sopra
    0.54
     извър
    0.49
     препо
    0.48
    h
    0.46
    াপি
    0.46
     acima
    0.44
    gunaan
    0.43
    باس
    0.43
    centage
    0.43
    ত
    0.43
    Activations Density 0.000%

    No Known Activations