© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61154
    Prev
    Next
    INDEX
    Explanations

    to to

    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_2_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
     to
    1.24
    ש
    1.13
    0
    1.07
    {
    1.02
    s
    0.99
     at
    0.98
    ้
    0.95
    ه
    0.93
    া
    0.92
    র
    0.90
    POSITIVE LOGITS
    که
    0.82
    cione
    0.80
    きた
    0.79
     políticos
    0.78
    нің
    0.76
    árt
    0.75
    ‌ی
    0.75
    ли
    0.75
    ého
    0.73
    де
    0.72
    Activations Density 0.003%

    No Known Activations