© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12289
    Prev
    Next
    INDEX
    Explanations

    shall not be

    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_40_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
    Tens
    0.64
    几十
    0.61
     десятки
    0.61
     tens
    0.61
    几
    0.57
    Thousands
    0.55
    Hundreds
    0.55
    Several
    0.53
    幾
    0.53
     dozens
    0.52
    POSITIVE LOGITS
    "=
    0.39
     excerpts
    0.37
    oprene
    0.37
    创
    0.36
    ']=
    0.36
     should
    0.36
     Should
    0.35
     reverses
    0.35
     heavy
    0.35
     extracts
    0.35
    Activations Density 0.006%

    No Known Activations