© 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. 203707
    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
    क्‍त
    0.44
     "-",
    0.41
     CIRC
    0.40
     PAY
    0.40
     ".",
    0.39
     unsatisf
    0.39
     Macintosh
    0.38
     Carrie
    0.38
     Heels
    0.38
     `:`,
    0.38
    POSITIVE LOGITS
    ţiile
    0.39
    териа
    0.39
     tunnelling
    0.38
    νοι
    0.37
     Twentieth
    0.37
    úng
    0.36
     returned
    0.35
     distintas
    0.35
     tillbaka
    0.35
    μων
    0.35
    Activations Density 0.000%

    No Known Activations