© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161606
    Prev
    Next
    INDEX
    Explanations

    use this

    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_2_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
     it
    1.27
     I
    1.18
     It
    1.16
    It
    1.16
    み
    1.05
     THAT
    0.94
    ?
    0.94
     Amtrak
    0.93
    ning
    0.93
     ८
    0.91
    POSITIVE LOGITS
    고
    1.14
     has
    1.13
    ை
    1.00
     destacados
    0.99
    ת
    0.93
     нажа
    0.90
    な
    0.88
    ა
    0.87
    ad
    0.85
    تين
    0.84
    Activations Density 0.000%

    No Known Activations