© 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. 76268
    Prev
    Next
    INDEX
    Explanations

    action: make, get, buy, write, build, do

    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
     გვ
    0.38
    دق
    0.37
    秉
    0.37
     rö
    0.36
    メソッド
    0.35
     antecedent
    0.35
     والد
    0.35
    込み
    0.35
     vô
    0.34
    剻
    0.34
    POSITIVE LOGITS
    Charl
    0.38
     resigning
    0.37
    enei
    0.36
     Replace
    0.36
    Restart
    0.36
    Buildable
    0.35
    ций
    0.35
    nad
    0.35
     REPLACE
    0.35
     plastics
    0.34
    Activations Density 0.011%

    No Known Activations