© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194364
    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_27_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
     –
    0.40
     कंधे
    0.40
     Operating
    0.39
     Calculus
    0.39
     Operators
    0.38
     Lime
    0.38
    Operators
    0.37
    calo
    0.37
     Concurrent
    0.36
     [,
    0.35
    POSITIVE LOGITS
    ರುವುದರಿಂದ
    0.41
    ികിത്സ
    0.41
    nitrogen
    0.40
    सु
    0.40
     bieten
    0.40
     chanson
    0.40
    മ്ബ
    0.38
    newPage
    0.38
     estánd
    0.37
    نگی
    0.37
    Activations Density 0.000%

    No Known Activations