© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217255
    Prev
    Next
    INDEX
    Explanations

    Midtown

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     Imper
    0.40
     imper
    0.39
    ANCH
    0.39
    BASELINE
    0.38
    yaml
    0.38
    ларды
    0.38
    𝐛
    0.38
     மேற்பர
    0.37
    ancher
    0.37
    бле
    0.37
    POSITIVE LOGITS
     morph
    0.39
    ather
    0.39
     kes
    0.38
    owsky
    0.38
    --;
    0.38
     spruce
    0.38
     swimming
    0.36
    Wishing
    0.36
     stages
    0.35
     mim
    0.35
    Activations Density 0.000%

    No Known Activations