© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195185
    Prev
    Next
    INDEX
    Explanations

    aho ǎng likelihood

    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_15_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
     any
    0.53
     non
    0.49
    we
    0.49
     हर
    0.49
     $
    0.48
     ל
    0.47
    i
    0.46
     rendah
    0.46
    l
    0.46
    f
    0.46
    POSITIVE LOGITS
     Crusaders
    0.51
    நீங்கள்
    0.50
    urados
    0.49
    ἃ
    0.48
     audiovisual
    0.48
    ர்களுக்கு
    0.48
    ارو
    0.47
     সেনাদের
    0.47
     মেয়েটি
    0.47
    Army
    0.47
    Activations Density 0.000%

    No Known Activations