© 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. 112133
    Prev
    Next
    INDEX
    Explanations

    search

    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
    ма
    1.52
    س
    1.51
    ری
    1.45
    ম
    1.41
    ك
    1.41
     ότι
    1.40
     it
    1.38
     rozwiąz
    1.35
    この
    1.33
    ৩
    1.32
    POSITIVE LOGITS
    n
    1.15
    ר
    1.03
    el
    1.00
    li
    0.94
    ťaž
    0.93
    s
    0.93
    er
    0.90
    th
    0.90
    chaft
    0.90
    ität
    0.90
    Activations Density 0.007%

    No Known Activations