© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33071
    Prev
    Next
    INDEX
    Explanations

    that clauses

    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_40_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
    Ⲧ
    0.41
     गहरी
    0.40
    BY
    0.39
    TD
    0.38
     Tob
    0.38
     синх
    0.38
     Нью
    0.37
    New
    0.37
    etto
    0.37
     ку
    0.37
    POSITIVE LOGITS
     WAV
    0.44
    }[(
    0.40
     ratings
    0.39
    aniy
    0.39
     περι
    0.39
    wav
    0.38
     표시
    0.38
    WillAppear
    0.37
     Wav
    0.37
     wav
    0.37
    Activations Density 0.061%

    No Known Activations