© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26062
    Prev
    Next
    INDEX
    Explanations

    makeup palette, applied, natural, flawless

    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_10_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
    ètres
    0.29
    чені
    0.26
    賃
    0.25
    ረጃ
    0.25
    carbonate
    0.25
    ст
    0.25
    ávání
    0.25
     tripartite
    0.25
    و
    0.25
     thrombo
    0.24
    POSITIVE LOGITS
    ile
    0.30
    yi
    0.28
     He
    0.26
     That
    0.25
     f
    0.25
     An
    0.25
    ie
    0.25
     As
    0.25
    w
    0.25
     Ange
    0.24
    Activations Density 0.016%

    No Known Activations