© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202222
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
     букмекерлик
    0.95
     रूपए
    0.93
    0.91
     raggiungere
    0.88
    ’
    0.88
     tinge
    0.88
    आई
    0.87
     سيكون
    0.87
     severely
    0.87
    ín
    0.82
    POSITIVE LOGITS
    s
    1.70
     to
    1.59
    ל
    1.55
    ים
    1.49
    ח
    1.28
    א
    1.23
    л
    1.22
    k
    1.18
    j
    1.16
    d
    1.15
    Activations Density 0.000%

    No Known Activations