© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28012
    Prev
    Next
    INDEX
    Explanations

    @

    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_40_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
    iany
    0.37
    ට්ට
    0.36
     अरब
    0.35
    lat
    0.34
     tangents
    0.34
     Sting
    0.34
    addLine
    0.33
    石
    0.33
    ம
    0.33
    ानि
    0.33
    POSITIVE LOGITS
    ILabel
    0.38
     softness
    0.38
    NEAPOLIS
    0.37
     spes
    0.36
     fleeing
    0.36
    越し
    0.35
    ∑
    0.35
    лук
    0.34
     annotation
    0.34
     notas
    0.34
    Activations Density 0.000%

    No Known Activations