© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33794
    Prev
    Next
    INDEX
    Explanations

    two 1s

    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
    2
    0.84
     for
    0.83
    3
    0.83
    '
    0.79
    ’
    0.75
    li
    0.73
    1
    0.69
    ll
    0.65
    de
    0.63
    cn
    0.63
    POSITIVE LOGITS
    ন
    0.79
    ن
    0.70
    น่า
    0.68
     caoutch
    0.67
     opsi
    0.66
     زیادی
    0.65
    共に
    0.64
     ઘણી
    0.64
     arrondies
    0.64
     clove
    0.63
    Activations Density 0.008%

    No Known Activations