© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176253
    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_24_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
     drž
    0.50
     Laufe
    0.43
    ^{(
    0.42
    扮
    0.42
     Jeżeli
    0.40
    
    0.40
     beispielsweise
    0.39
     Crews
    0.39
     Cached
    0.38
     ไม
    0.38
    POSITIVE LOGITS
    óloga
    0.48
    kingdom
    0.46
    won
    0.46
    <0x0D>
    0.45
    tr
    0.45
    res
    0.44
    active
    0.44
    resi
    0.44
    োর্স
    0.44
    গরে
    0.44
    Activations Density 0.000%

    No Known Activations