© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135703
    Prev
    Next
    INDEX
    Explanations

    end of code block

    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
    aje
    0.38
     nin
    0.38
    :(
    0.36
    Usuarios
    0.36
     XXX
    0.35
     iso
    0.35
    ęs
    0.35
     ១
    0.35
     medicines
    0.35
     monsters
    0.35
    POSITIVE LOGITS
    狽
    0.39
     आपस
    0.39
     пога
    0.37
    હા
    0.37
    กับการ
    0.37
    haps
    0.36
    htaking
    0.36
     উইকেট
    0.36
    ার্ভ
    0.36
    赤い
    0.35
    Activations Density 0.000%

    No Known Activations