© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151061
    Prev
    Next
    INDEX
    Explanations

    mid

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ́ch
    0.37
    耆
    0.35
    ancha
    0.34
    それに
    0.33
    a
    0.33
    نګ
    0.33
    路
    0.33
    ઠ
    0.32
    ```
    0.32
    at
    0.32
    POSITIVE LOGITS
     journey
    2.61
    journey
    2.33
    Journey
    2.25
     Journey
    2.16
     journeys
    1.84
     JOUR
    1.76
     perjalanan
    1.48
    jour
    1.22
     Jour
    1.18
     सफर
    1.14
    Activations Density 0.002%

    No Known Activations