© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    calendar months

    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
     Fast
    0.43
     Compens
    0.41
     Flesh
    0.38
     একেবারে
    0.37
    াকার
    0.37
     ፈ
    0.37
    cas
    0.36
    Fre
    0.35
     Prepared
    0.35
    quero
    0.34
    POSITIVE LOGITS
     তারিখে
    0.40
     रोजी
    0.38
     mặc
    0.37
     പാറ
    0.36
     พัน
    0.36
    એ
    0.36
    пова
    0.35
     saat
    0.35
     दिन
    0.34
     Châu
    0.34
    Activations Density 0.003%

    No Known Activations