© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214904
    Prev
    Next
    INDEX
    Explanations

    Hawaiian place names and words

    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_5_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
    at
    1.31
    en
    1.08
    ap
    1.02
    un
    1.00
    ين
    0.98
     collusion
    0.97
    im
    0.91
    w
    0.90
     makeshift
    0.90
    op
    0.89
    POSITIVE LOGITS
    ।
    1.11
    。
    1.09
    </h4>
    1.00
    нер
    0.93
    ။
    0.93
    کنندگان
    0.92
    }{
    0.89
    _
    0.89
    тира
    0.85
    ką
    0.84
    Activations Density 0.000%

    No Known Activations