© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116087
    Prev
    Next
    INDEX
    Explanations

    SQL statement endings

    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_27_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
     ;,
    0.41
     밝혔다
    0.36
    ,,
    0.34
     SECTION
    0.34
     –
    0.34
     шанс
    0.34
     *);
    0.33
     चु
    0.33
     classic
    0.33
     සි
    0.33
    POSITIVE LOGITS
    Served
    0.44
    asmuch
    0.43
    orphous
    0.43
    țial
    0.43
    Crud
    0.42
    Sun
    0.42
    getServer
    0.42
     omdat
    0.41
    Rpc
    0.41
    సుకొ
    0.41
    Activations Density 0.001%

    No Known Activations