© 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. 127481
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years or durations

    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
     வயது
    0.38
     Refunds
    0.37
     العشر
    0.37
    旌
    0.37
    tw
    0.36
    itters
    0.36
    tween
    0.35
     عائد
    0.34
     tw
    0.34
     anode
    0.34
    POSITIVE LOGITS
    㣩
    0.40
     lifelong
    0.40
    گیری
    0.38
    کلی
    0.38
    ាប់
    0.38
     Kubrick
    0.37
     lifetime
    0.37
    čky
    0.37
     Breite
    0.37
     क्षार
    0.37
    Activations Density 0.002%

    No Known Activations