© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 149209
    Prev
    Next
    INDEX
    Explanations

    the number 1

    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
    °)
    0.48
    ₂)
    0.48
     ?)
    0.45
    __).
    0.43
    ²)
    0.43
    .”)
    0.43
    ”),
    0.43
    {})
    0.42
    ”).
    0.42
    
    0.42
    POSITIVE LOGITS
    ,$
    0.53
     but
    0.44
     Not
    0.43
    ,\\
    0.42
     not
    0.41
    ,$
    0.40
     maar
    0.40
     transporters
    0.40
    !
    0.38
     लेकिन
    0.37
    Activations Density 0.002%

    No Known Activations