© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230511
    Prev
    Next
    INDEX
    Explanations

    compound interest

    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_6_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
    1.31
    p
    1.26
    r
    1.13
    s
    1.13
    m
    1.05
    d
    0.97
    ز
    0.90
    j
    0.89
    n
    0.88
    al
    0.84
    POSITIVE LOGITS
    した
    1.09
    and
    1.08
    Y
    1.06
    การ
    1.04
    人々
    0.98
    बी
    0.96
    یس
    0.96
    یک
    0.95
    وری
    0.95
     ولی
    0.94
    Activations Density 0.000%

    No Known Activations