© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23135
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    -
    0.76
    ־
    0.64
    ‐
    0.61
    ‑
    0.58
    −
    0.54
    ﹣
    0.48
    -​
    0.47
    
    0.46
    -*
    0.45
    
    0.41
    POSITIVE LOGITS
    )}$-
    0.37
     indispens
    0.37
     indispensable
    0.36
    )-,
    0.36
     indispensables
    0.34
     &-
    0.33
    separ
    0.32
     -,
    0.32
     muster
    0.32
     malle
    0.31
    Activations Density 0.064%

    No Known Activations