© 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. 201079
    Prev
    Next
    INDEX
    Explanations

    creative solutions

    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_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
    </td>
    1.19
    ’
    1.05
     αλλά
    0.99
     in
    0.97
     aggreg
    0.95
     appell
    0.95
     INSEE
    0.94
     inns
    0.94
     assemblages
    0.94
     enunci
    0.93
    POSITIVE LOGITS
    лос
    0.82
    ми
    0.81
    o
    0.78
    AT
    0.77
    ीत
    0.77
    мит
    0.75
    و
    0.74
     xưa
    0.74
    ба
    0.72
    oises
    0.71
    Activations Density 0.006%

    No Known Activations