© 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. 35667
    Prev
    Next
    INDEX
    Explanations

    enough size or extent

    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
     outlay
    0.52
     ascertaining
    0.51
     सटीक
    0.50
     ascertain
    0.49
    )$
    0.49
     heartache
    0.48
     तकलीफ
    0.47
     считают
    0.47
     Nxe
    0.46
     जैसी
    0.45
    POSITIVE LOGITS
    لع
    0.54
    orsement
    0.52
    mals
    0.51
     silenced
    0.51
     is
    0.50
    s
    0.50
     escolas
    0.50
     celulares
    0.50
     enormes
    0.50
    t
    0.49
    Activations Density 0.003%

    No Known Activations