© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193214
    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_4_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
    fitted
    0.43
     scallop
    0.43
     MFP
    0.43
    aties
    0.43
     fitted
    0.42
    弃
    0.42
    "><
    0.42
     SRP
    0.42
     htob
    0.42
     chaff
    0.41
    POSITIVE LOGITS
    രാ
    0.49
    Families
    0.45
     Сьогодні
    0.44
    vad
    0.44
     considerare
    0.44
    ﻞ
    0.44
    Replacing
    0.43
     ricordare
    0.43
     valle
    0.43
     storie
    0.43
    Activations Density 0.000%

    No Known Activations