© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115481
    Prev
    Next
    INDEX
    Explanations

    just is

    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_27_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
    ల్లు
    0.41
     делают
    0.38
    관계
    0.38
     பாரம்பரிய
    0.37
     ALL
    0.37
     любую
    0.36
    櫚
    0.36
     verses
    0.36
     ALSO
    0.36
    оборот
    0.35
    POSITIVE LOGITS
    ichier
    0.43
    </i>
    0.40
    раи
    0.40
    Geocoder
    0.40
     однако
    0.39
    raison
    0.39
     Gynecol
    0.39
     apenas
    0.38
     devait
    0.38
     Drummond
    0.38
    Activations Density 0.009%

    No Known Activations