© 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. 60551
    Prev
    Next
    INDEX
    Explanations

    ches, usses

    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
    д
    1.53
    لي
    1.36
    d
    1.36
    is
    1.30
    يد
    1.29
    ל
    1.27
    ש
    1.27
    די
    1.22
    lerine
    1.19
    li
    1.18
    POSITIVE LOGITS
    >
    1.27
    การ
    1.22
    好
    1.09
    $
    1.09
    the
    1.06
    ุ
    1.05
     definitiv
    1.00
    를
    1.00
     در
    0.99
    2
    0.98
    Activations Density 0.000%

    No Known Activations