© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18284
    Prev
    Next
    INDEX
    Explanations

    innerspring coils or pocket slots

    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_40_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
    ❇
    0.39
    itaan
    0.39
    Beans
    0.38
    Jur
    0.38
    idor
    0.38
     clearTimeout
    0.37
    霭
    0.37
     पर्व
    0.36
    ⛳
    0.36
     Beans
    0.36
    POSITIVE LOGITS
     pocket
    0.58
    pocket
    0.50
    Pocket
    0.46
     Pocket
    0.44
     slot
    0.41
    ポケット
    0.41
     coils
    0.40
    ecc
    0.39
     responsive
    0.38
    स्टेप
    0.37
    Activations Density 0.011%

    No Known Activations