© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180774
    Prev
    Next
    INDEX
    Explanations

    SQL INDEX statements

    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_24_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
     Desar
    0.40
    业界
    0.38
    J
    0.38
     Саме
    0.38
    mère
    0.38
    ﻗ
    0.37
    uzioni
    0.37
    عند
    0.37
    على
    0.37
    father
    0.36
    POSITIVE LOGITS
     효과
    0.41
    ignac
    0.40
     clings
    0.40
     తీసుకు
    0.39
    ubhav
    0.38
    órias
    0.38
     potreb
    0.37
    ടിച്ച
    0.37
     driv
    0.37
    }}}=
    0.37
    Activations Density 0.000%

    No Known Activations