© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109551
    Prev
    Next
    INDEX
    Explanations

    two-dimensional arrays

    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
    ล
    0.97
    ট
    0.93
     inizia
    0.92
    其他
    0.92
    考え
    0.91
     empieza
    0.91
     azione
    0.91
    larda
    0.89
    ו
    0.89
    オーダー
    0.88
    POSITIVE LOGITS
    a
    1.34
     by
    1.24
    ing
    1.16
    ى
    1.11
     with
    1.08
    ’
    1.07
    я
    1.03
    на
    1.02
    ne
    1.00
    ви
    0.98
    Activations Density 0.000%

    No Known Activations