© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241117
    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_25_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
    (":
    0.47
     भने
    0.42
    (':
    0.41
    Fees
    0.39
     بها
    0.39
     chủ
    0.38
     agres
    0.37
     representando
    0.37
    ags
    0.37
     सतर्क
    0.36
    POSITIVE LOGITS
     gradation
    0.41
     astral
    0.39
     hexane
    0.38
     stub
    0.38
     Mariupol
    0.38
     frustration
    0.37
     두
    0.37
    两
    0.37
    춧
    0.37
     promptly
    0.36
    Activations Density 0.000%

    No Known Activations