© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92400
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_60_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
    5
    0.62
    1
    0.57
    6
    0.54
    8
    0.53
    2
    0.53
    4
    0.53
    7
    0.53
    3
    0.41
    9
    0.37
    0
    0.31
    POSITIVE LOGITS
    thirty
    0.27
     फरवरी
    0.26
     second
    0.26
    second
    0.26
     segunda
    0.26
     February
    0.25
    January
    0.25
    ⴻ
    0.25
     nineties
    0.25
     SECOND
    0.24
    Activations Density 0.000%

    No Known Activations