© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211218
    Prev
    Next
    INDEX
    Explanations

    sine and cosine functions

    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_20_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
     coleção
    0.44
     teoria
    0.44
    ᓃ
    0.41
     antiga
    0.40
     isometric
    0.39
     vati
    0.39
     ඕ
    0.38
     estudo
    0.38
     teoría
    0.38
     gory
    0.38
    POSITIVE LOGITS
    CK
    0.39
    </b>
    0.37
    OUT
    0.33
     Lumi
    0.33
    sType
    0.33
    mV
    0.32
    out
    0.32
    <0xE2>
    0.31
    CT
    0.31
    ünsche
    0.31
    Activations Density 0.003%

    No Known Activations