© 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. 161374
    Prev
    Next
    INDEX
    Explanations

    Vellum, Nusantara, Rahman

    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
    の
    1.30
    ко
    1.26
    的其他
    1.14
    كان
    1.11
    ર
    1.11
     superfici
    1.08
    ও
    1.08
     в
    1.07
    га
    1.06
    其他
    1.06
    POSITIVE LOGITS
    il
    1.65
    n
    1.60
    ↵
    1.52
     for
    1.31
    el
    1.24
    3
    1.09
    mu
    1.07
    this
    1.05
    i
    1.05
    log
    1.00
    Activations Density 0.000%

    No Known Activations