© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39500
    Prev
    Next
    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Iam
    0.54
    am
    0.52
    iam
    0.50
     Cham
    0.48
     Lam
    0.47
     there
    0.46
    암
    0.46
    ាម
    0.46
     kamm
    0.46
     ham
    0.46
    POSITIVE LOGITS
     nc
    0.58
     nic
    0.57
     nz
    0.54
     n
    0.52
     nb
    0.52
     nx
    0.52
     nil
    0.51
    nc
    0.51
    ncc
    0.49
     nov
    0.48
    Activations Density 0.001%

    No Known Activations