© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236279
    Prev
    Next
    INDEX
    Explanations

    return False or True

    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_25_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
    の
    0.41
     bacterial
    0.41
     tanha
    0.38
     infus
    0.38
     sedimentary
    0.37
     aval
    0.37
     feel
    0.36
     Curve
    0.36
     Aval
    0.35
     rant
    0.35
    POSITIVE LOGITS
     uwagę
    0.39
    无疑
    0.38
    ستوى
    0.37
    PHOTO
    0.36
    诖
    0.36
    Frequently
    0.36
    otipos
    0.36
    igheden
    0.36
    Contrary
    0.36
    Sadly
    0.35
    Activations Density 0.001%

    No Known Activations