© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45980
    Prev
    Next
    INDEX
    Explanations

    rising, declining, power, strength

    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_13_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
    Mailer
    0.59
     接
    0.51
    <unused79>
    0.50
    ậc
    0.48
    ograms
    0.48
     सैलरी
    0.48
    ionario
    0.46
    EventArgs
    0.46
    żs
    0.46
    BarButtonItem
    0.46
    POSITIVE LOGITS
     velho
    0.49
    uestro
    0.48
     earthly
    0.44
    UND
    0.44
     дә
    0.44
     дополни
    0.43
    дә
    0.42
    `/
    0.42
     CIVIL
    0.42
     restore
    0.42
    Activations Density 0.024%

    No Known Activations