© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50033
    Prev
    Next
    INDEX
    Explanations

    `Fibonacci sequences` or `squares` or `park`

    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
     Nella
    0.45
    व
    0.42
     אם
    0.42
     bogey
    0.42
     Lokal
    0.42
     Antit
    0.41
    jším
    0.41
     Geschä
    0.41
    Leod
    0.41
     COURT
    0.41
    POSITIVE LOGITS
    g
    0.61
    p
    0.54
    disable
    0.54
    us
    0.53
     disable
    0.52
    usd
    0.52
    gd
    0.49
    capitalize
    0.48
     تباہ
    0.48
    oh
    0.47
    Activations Density 0.000%

    No Known Activations