© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170511
    Prev
    Next
    INDEX
    Explanations

    can

    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_56_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
     i
    0.50
     Be
    0.41
    ｉ
    0.41
     awaits
    0.40
    i
    0.39
     completa
    0.36
     below
    0.35
     Head
    0.35
     els
    0.34
    -(
    0.34
    POSITIVE LOGITS
     do
    0.47
     ..."
    0.39
    䤚
    0.38
    :\
    0.38
    :'
    0.37
    :”
    0.37
     …”
    0.36
    ヶ
    0.35
    燄
    0.35
    عل
    0.35
    Activations Density 0.010%

    No Known Activations