© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212231
    Prev
    Next
    INDEX
    Explanations

    names starting with en- or related to Tolkien / fantasy

    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
    ான்
    0.88
    ありますが
    0.88
    τα
    0.87
     ちゃん
    0.85
    он
    0.82
    د
    0.79
    ။
    0.79
    ام
    0.78
     произошло
    0.77
     bericht
    0.77
    POSITIVE LOGITS
    the
    1.26
    1.16
    You
    0.92
    in
    0.89
    They
    0.88
    ks
    0.83
    eine
    0.83
    These
    0.80
    If
    0.79
    an
    0.78
    Activations Density 0.000%

    No Known Activations