© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199671
    Prev
    Next
    INDEX
    Explanations

    URLs and tags

    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_50_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
     G
    0.68
    G
    0.60
     গ
    0.55
     ग
    0.50
    ဂ
    0.50
     گ
    0.46
    Ｇ
    0.44
     ग्वालियर
    0.43
     ഗ
    0.43
    Ꮐ
    0.42
    POSITIVE LOGITS
     Bog
    0.43
     twisted
    0.42
     Pilgrim
    0.42
    eci
    0.41
     KING
    0.41
     Twisted
    0.40
     Bull
    0.40
     왕
    0.40
     Bullock
    0.40
     ペ
    0.39
    Activations Density 0.000%

    No Known Activations