© 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. 108089
    Prev
    Next
    INDEX
    Explanations

    al, alla, or a combination

    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
    n
    2.25
    la
    1.77
    ن
    1.77
    s
    1.63
    et
    1.52
    3
    1.49
    ra
    1.45
    н
    1.42
    li
    1.41
    lt
    1.34
    POSITIVE LOGITS
    1.23
    cı
    1.13
    ৫
    1.13
    し
    1.13
    ент
    1.04
     وه
    1.03
    是我们
    1.02
    是最
    1.02
    ウ
    0.97
    共に
    0.96
    Activations Density 0.001%

    No Known Activations