© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48001
    Prev
    Next
    INDEX
    Explanations

    container

    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_10_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
    i
    0.68
    c
    0.67
    g
    0.62
     ре
    0.62
     ray
    0.61
    d
    0.61
     barrier
    0.59
     verwend
    0.58
    ية
    0.57
     马
    0.57
    POSITIVE LOGITS
     powied
    0.76
    ش
    0.70
    ના
    0.69
    اه
    0.68
    ﻂ
    0.67
    sparsity
    0.66
    ন
    0.66
    żej
    0.65
    اء
    0.64
    न
    0.64
    Activations Density 0.001%

    No Known Activations