© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ى
    1.06
    ير
    0.79
    般的
    0.75
     σε
    0.75
    போன்ற
    0.74
    ளை
    0.74
    до
    0.73
    feas
    0.73
     in
    0.71
    ونه
    0.71
    POSITIVE LOGITS
    s
    1.40
    ی
    0.98
    น
    0.93
    d
    0.85
    н
    0.85
    ન
    0.85
    ni
    0.84
    j
    0.83
     जिम्मेदार
    0.82
    t
    0.78
    Activations Density 0.000%

    No Known Activations