© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21400
    Prev
    Next
    INDEX
    Explanations

    say punctuation

    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_56_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
     jem
    0.40
     optimized
    0.36
    运输
    0.35
     Avner
    0.34
    }}^{*}
    0.33
    탉
    0.33
    ("/")
    0.33
     hadron
    0.33
     soru
    0.33
    請問
    0.33
    POSITIVE LOGITS
     ?.
    0.61
    ’.
    0.51
     گی۔
    0.48
     ».
    0.48
    ».
    0.48
    ’).
    0.45
    ?.
    0.44
    €.
    0.43
    Neigh
    0.43
    」。
    0.42
    Activations Density 0.098%

    No Known Activations