© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205841
    Prev
    Next
    INDEX
    Explanations

    computer obtain deceive

    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_37_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
    Home
    0.40
    direccion
    0.38
    還元
    0.38
    '}$
    0.37
     aislado
    0.36
     स्टेन
    0.36
    的最佳
    0.36
    Adventure
    0.36
     leche
    0.35
     ಅನುಪಾತ
    0.35
    POSITIVE LOGITS
    弦
    0.40
    brar
    0.40
    蝌
    0.39
    QRST
    0.36
    犍
    0.36
     circuit
    0.35
    HHHH
    0.34
     string
    0.34
    鏁
    0.34
    ខ្សែ
    0.33
    Activations Density 0.002%

    No Known Activations