© 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. 135023
    Prev
    Next
    INDEX
    Explanations

    wt% SiO2

    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
     Acer
    0.42
    ให้
    0.39
     horizont
    0.38
     sloping
    0.38
     Nazis
    0.38
     ह
    0.38
    Mounted
    0.38
     hr
    0.38
    Drawer
    0.38
     Dep
    0.38
    POSITIVE LOGITS
    ')}
    0.40
    órmula
    0.39
    ಂಡ
    0.37
    ocols
    0.37
    برد
    0.37
     vork
    0.36
    vrdr
    0.36
    DebugInformation
    0.36
    ')).
    0.36
    뻑
    0.35
    Activations Density 0.000%

    No Known Activations