© 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. 13818
    Prev
    Next
    INDEX
    Explanations

    response after question

    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
    ن
    0.62
    ierstrass
    0.51
     их
    0.49
    )$,
    0.47
     bisogno
    0.47
     சா
    0.47
    ソ
    0.46
     subsection
    0.46
     humains
    0.46
     έως
    0.46
    POSITIVE LOGITS
    TestAction
    0.54
     العالمية
    0.51
    ປະກ
    0.50
    Link
    0.46
     />}/>
    0.46
    metaTag
    0.45
    CrossOrigin
    0.45
     Physica
    0.45
     Française
    0.45
     Filme
    0.44
    Activations Density 0.000%

    No Known Activations