© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177693
    Prev
    Next
    INDEX
    Explanations

    after alone

    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_29_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
     dokładnie
    0.42
     caviar
    0.40
     touche
    0.39
     ސ
    0.38
     ඒ
    0.38
     théorie
    0.37
     signe
    0.37
    ង់
    0.36
     burger
    0.36
    利益
    0.36
    POSITIVE LOGITS
     convening
    0.41
    一覧
    0.38
     учеб
    0.38
    Forward
    0.37
    READ
    0.37
     pausing
    0.36
    {
    0.35
    iyet
    0.35
    daftar
    0.35
    稚
    0.34
    Activations Density 0.001%

    No Known Activations