© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200758
    Prev
    Next
    INDEX
    Explanations

    nice to meet you

    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_6_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
    ти
    1.12
    -
    0.91
    し
    0.85
    the
    0.84
    л
    0.84
    padă
    0.82
    נה
    0.82
    і
    0.81
    ți
    0.78
    ”)
    0.78
    POSITIVE LOGITS
    。
    0.96
    ।।
    0.88
    ।
    0.84
    ول
    0.82
     وطالبات
    0.82
     be
    0.81
     it
    0.79
     at
    0.79
    。\
    0.75
    ।’
    0.74
    Activations Density 0.001%

    No Known Activations