© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45448
    Prev
    Next
    INDEX
    Explanations

    apply knowledge

    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_22_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
    વાડી
    0.42
    ဆေး
    0.38
     tramite
    0.37
     بودم
    0.36
    槸
    0.36
     pouvoir
    0.36
     chlorophyll
    0.36
     উপকার
    0.36
     ఆరోగ
    0.35
     الاص
    0.35
    POSITIVE LOGITS
     өт
    0.44
     langt
    0.44
    percent
    0.42
     конкурен
    0.42
     рынок
    0.40
     Андрей
    0.40
    enough
    0.40
    횟
    0.39
         
    0.39
     enough
    0.39
    Activations Density 0.006%

    No Known Activations