© 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. 58901
    Prev
    Next
    INDEX
    Explanations

    juxtaposition

    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
    '
    1.13
    inen
    1.01
     disgruntled
    0.97
    '=
    0.94
    gewicht
    0.90
    েরা
    0.88
     ግራም
    0.88
     χρόνο
    0.88
    ’)
    0.85
    ’;
    0.84
    POSITIVE LOGITS
    し
    2.02
    ל
    1.50
    n
    1.34
    ل
    1.33
    ž
    1.33
    ä
    1.30
    ル
    1.26
    ق
    1.23
    f
    1.21
    ল
    1.17
    Activations Density 0.000%

    No Known Activations