© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35477
    Prev
    Next
    INDEX
    Explanations

    yogurt parfait

    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_3_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
    л
    1.26
    ل
    1.20
    ל
    0.91
    ल
    0.89
    લ
    0.88
    υ
    0.88
    ی
    0.87
    க
    0.86
    이를
    0.82
    نی
    0.82
    POSITIVE LOGITS
    2
    1.13
    was
    0.97
    '
    0.90
    de
    0.84
     was
    0.81
    c
    0.81
    5
    0.80
    7
    0.75
    word
    0.73
    a
    0.71
    Activations Density 0.001%

    No Known Activations