© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225461
    Prev
    Next
    INDEX
    Explanations

    you or me

    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_10_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
    iquement
    0.32
    ре
    0.30
    :
    0.29
    af
    0.29
    ין
    0.28
    vaient
    0.28
    ከር
    0.28
    aft
    0.28
    arı
    0.28
    UART
    0.28
    POSITIVE LOGITS
     I
    0.33
     Polymer
    0.28
    I
    0.28
    ,"
    0.26
     IMPORT
    0.26
    E
    0.25
     O
    0.25
     വസ്തു
    0.24
     వ
    0.23
     IB
    0.23
    Activations Density 0.009%

    No Known Activations