© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16325
    Prev
    Next
    INDEX
    Explanations

    Divide both sides

    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
    imposed
    0.44
     imposed
    0.41
     retiring
    0.40
    锏
    0.39
     池
    0.38
    axiom
    0.38
     advancing
    0.37
    資格
    0.37
    ȟ
    0.37
     principle
    0.37
    POSITIVE LOGITS
    aviti
    0.37
     Ith
    0.36
    icional
    0.35
     Ша
    0.34
    нити
    0.34
     puntu
    0.34
     ارزش
    0.34
    ieu
    0.34
     calcul
    0.33
     তো
    0.33
    Activations Density 0.011%

    No Known Activations