© 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. 35883
    Prev
    Next
    INDEX
    Explanations

    good deeds

    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
    在
    0.85
    Request
    0.80
    ס
    0.79
    ため
    0.77
    Repository
    0.77
    ד
    0.76
    ৫
    0.75
    って
    0.73
    с
    0.73
    az
    0.73
    POSITIVE LOGITS
    an
    0.82
    ان
    0.71
     necks
    0.68
     темы
    0.68
     garnished
    0.65
     equivari
    0.63
     специализирован
    0.63
    sembles
    0.61
     рам
    0.61
     ramps
    0.60
    Activations Density 0.021%

    No Known Activations