© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193402
    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_9_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ),
    0.59
     contained
    0.55
    ’,
    0.54
     gated
    0.53
     kan
    0.52
     झालेले
    0.50
    )
    0.49
    」、
    0.48
     held
    0.48
     vân
    0.48
    POSITIVE LOGITS
    ط
    0.54
    فل
    0.54
     Offenders
    0.50
    阃
    0.50
    鹘
    0.50
    مار
    0.48
    мир
    0.48
    measure
    0.47
    Ку
    0.47
    𝓪
    0.47
    Activations Density 0.000%

    No Known Activations