© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35921
    Prev
    Next
    INDEX
    Explanations

    mile marker, league, distance

    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_11_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
    et
    0.59
     her
    0.52
    ž
    0.52
    by
    0.51
    š
    0.50
    ag
    0.50
    ak
    0.49
    q
    0.49
    it
    0.48
    }$
    0.48
    POSITIVE LOGITS
     часу
    0.47
    detectChanges
    0.46
     costituito
    0.46
    ність
    0.46
    路撒
    0.46
     consacré
    0.45
     تاريخ
    0.44
     предоставля
    0.44
     گور
    0.44
     distinta
    0.43
    Activations Density 0.005%

    No Known Activations