© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196013
    Prev
    Next
    INDEX
    Explanations

    context/code blocks

    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_27_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
     eryth
    0.35
     बातें
    0.34
     wl
    0.34
     کرتا
    0.33
     Lactobacillus
    0.33
    骗
    0.33
     Fuel
    0.33
     CRO
    0.33
     Santa
    0.32
    )}^{\
    0.32
    POSITIVE LOGITS
    Adjacent
    0.37
    zeit
    0.34
    tapping
    0.34
    spanning
    0.33
     rafts
    0.33
    Marne
    0.33
     ампли
    0.33
    廂
    0.32
    Aware
    0.32
    adjacent
    0.32
    Activations Density 0.000%

    No Known Activations