© 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. 180004
    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
    Num
    0.53
     bezpośred
    0.52
    Dere
    0.50
    Ship
    0.49
     середи
    0.48
    Ｕ
    0.48
     atualmente
    0.47
    Flu
    0.46
     appartiennent
    0.46
    Atoi
    0.46
    POSITIVE LOGITS
     excesses
    0.51
     to
    0.50
    ਹ
    0.48
     conclusions
    0.47
     mistakes
    0.46
    ంట
    0.45
     closer
    0.45
     examinations
    0.44
     cliffs
    0.44
    ции
    0.44
    Activations Density 0.000%

    No Known Activations