© 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. 180012
    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
     intramolecular
    0.37
    AppState
    0.37
    把
    0.36
     کمپیوٹر
    0.36
     CAGR
    0.36
     Loading
    0.35
     naprawdę
    0.34
     }}}
    0.34
     başına
    0.34
     Algebras
    0.33
    POSITIVE LOGITS
    attoo
    0.46
     หลาย
    0.43
    суз
    0.42
    arl
    0.41
    raid
    0.40
    idla
    0.40
    ंगली
    0.40
    inesh
    0.40
    urel
    0.40
    wood
    0.39
    Activations Density 0.000%

    No Known Activations