© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 77934
    Prev
    Next
    INDEX
    Explanations

    academic affiliations and famous figures

    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_31_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
     profes
    0.41
     manoeuvre
    0.40
    дона
    0.40
    ందం
    0.40
     ಶ
    0.39
     manoe
    0.39
     masterful
    0.38
     manoeuv
    0.37
    ству
    0.36
    ेंगू
    0.36
    POSITIVE LOGITS
    <table>
    0.44
    <start_of_image>
    0.44
    并通过
    0.42
     Tuition
    0.41
     Offered
    0.40
     Fact
    0.39
     Facts
    0.39
     Mel
    0.39
     Albright
    0.38
     Released
    0.38
    Activations Density 0.000%

    No Known Activations