© 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. 246522
    Prev
    Next
    INDEX
    Explanations

    something was / someone speaking

    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
     Constant
    0.39
     HashSet
    0.38
     Potts
    0.37
     constant
    0.36
     puse
    0.36
     Iterable
    0.36
     Landmark
    0.36
    谯
    0.35
     TLabel
    0.35
    Constant
    0.34
    POSITIVE LOGITS
    ቸ
    0.37
    成績
    0.36
    Installer
    0.36
    kara
    0.35
    츠
    0.34
     affrontare
    0.34
    ido
    0.33
     Entering
    0.33
     εγκα
    0.32
    鋒
    0.32
    Activations Density 0.003%

    No Known Activations