© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35854
    Prev
    Next
    INDEX
    Explanations

    confidence and ability to complete tasks

    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_31_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
    Ꮫ
    0.38
     wskaz
    0.38
     indication
    0.37
    athy
    0.37
     Indicates
    0.37
    icy
    0.37
     निर्देशा
    0.36
     indiquer
    0.36
    珣
    0.35
     indicates
    0.35
    POSITIVE LOGITS
     pomegranate
    0.39
    泳
    0.38
     ورژن
    0.38
    Modified
    0.37
     ფედერ
    0.37
     modified
    0.36
     institutional
    0.35
     aer
    0.35
     adjusted
    0.35
     NAC
    0.34
    Activations Density 0.000%

    No Known Activations