© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108090
    Prev
    Next
    INDEX
    Explanations

    Lindt, Excellence, Palindromic

    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_2_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
    r
    1.39
    x
    1.32
    t
    1.22
    li
    1.20
    ש
    1.20
    u
    1.20
    ط
    1.18
    l
    1.09
    ne
    1.07
    一
    1.07
    POSITIVE LOGITS
    ного
    1.25
    اری
    1.23
    ες
    1.17
    ка
    1.10
    ная
    1.05
    ным
    1.02
    ва
    1.00
    ิ
    0.93
    ատ
    0.93
    ید
    0.92
    Activations Density 0.000%

    No Known Activations