© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88526
    Prev
    Next
    INDEX
    Explanations

    Ravens, cart, bombs, x

    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
     jeopard
    0.70
    lN
    0.67
    ל
    0.65
    نى
    0.64
    lade
    0.64
    lige
    0.63
     is
    0.62
    lou
    0.61
    d
    0.61
    lL
    0.61
    POSITIVE LOGITS
    ை
    0.86
    ة
    0.85
    ता
    0.84
     که
    0.77
    ă
    0.77
    '
    0.72
    се
    0.70
    ü
    0.69
     سی
    0.67
    2
    0.66
    Activations Density 0.003%

    No Known Activations