© 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. 101767
    Prev
    Next
    INDEX
    Explanations

    δ charge, fragments, second, milliseconds

    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
     দিবার
    0.30
     trouv
    0.28
     suivent
    0.27
     FOREST
    0.27
     считает
    0.27
    ]&
    0.27
    чему
    0.26
     DCC
    0.26
    ᆹ
    0.26
     homeowners
    0.26
    POSITIVE LOGITS
    ed
    0.37
    n
    0.34
    s
    0.34
    of
    0.32
    es
    0.31
    on
    0.30
    able
    0.29
    as
    0.28
    N
    0.28
    F
    0.28
    Activations Density 0.005%

    No Known Activations