© 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. 162246
    Prev
    Next
    INDEX
    Explanations

    l, a, o, p, s, t, w, z

    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
    ում
    1.29
    ת
    1.27
    ラ
    1.24
    ード
    1.23
    ри
    1.22
    ה
    1.18
    ラの
    1.17
    ۳
    1.17
    ون
    1.12
    ック
    1.11
    POSITIVE LOGITS
    to
    1.64
    te
    1.45
    tt
    1.40
    ta
    1.39
    sk
    1.25
    ty
    1.23
    sh
    1.23
    th
    1.22
    ng
    1.22
    that
    1.21
    Activations Density 0.002%

    No Known Activations