© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90269
    Prev
    Next
    INDEX
    Explanations

    -

    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
    Were
    0.43
    8
    0.43
    Super
    0.41
    ึง
    0.40
    Elena
    0.40
    Dob
    0.38
    ังหวัด
    0.38
     entrance
    0.38
    Appeal
    0.38
    रिपोर्ट
    0.38
    POSITIVE LOGITS
    _
    0.56
    "
    0.53
     Life
    0.49
     Rem
    0.46
     Symbols
    0.46
    ",
    0.46
     Blocks
    0.46
     Tiles
    0.46
     Tabs
    0.46
    life
    0.46
    Activations Density 0.001%

    No Known Activations