© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97139
    Prev
    Next
    INDEX
    Explanations

    Adelaide, Australia

    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_14_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
    d
    0.58
     Hernandez
    0.55
    t
    0.53
    mtrl
    0.52
    avil
    0.51
    nance
    0.49
    ulam
    0.49
    ín
    0.48
     didik
    0.48
    ASHI
    0.48
    POSITIVE LOGITS
    Очень
    0.55
     Nickel
    0.52
     Cars
    0.51
    杮
    0.51
    בר
    0.50
     narzęd
    0.49
    ？！
    0.48
    Ско
    0.48
     NICKEL
    0.48
     ؟
    0.48
    Activations Density 0.000%

    No Known Activations