© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82347
    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_53_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
    Atoi
    0.43
    fir
    0.38
     Thir
    0.37
    input
    0.37
     ff
    0.37
    త్వం
    0.37
    麟
    0.36
    gp
    0.36
    uari
    0.36
     太
    0.36
    POSITIVE LOGITS
     Cs
    0.69
    CS
    0.69
     CS
    0.64
     सीएस
    0.60
    Cs
    0.59
     cs
    0.56
     cerebrospinal
    0.55
    cs
    0.54
     CSF
    0.52
     CSU
    0.50
    Activations Density 0.000%

    No Known Activations