© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241726
    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_40_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
    Javascript
    0.41
     depressions
    0.40
     poche
    0.39
    鿌
    0.39
     neurop
    0.38
    下降
    0.38
     '*':
    0.38
     depression
    0.38
     Javascript
    0.38
     zbior
    0.37
    POSITIVE LOGITS
     அ
    0.41
     Public
    0.39
     enlist
    0.39
     cortex
    0.38
     singkat
    0.38
    ssel
    0.38
     клас
    0.38
     score
    0.37
    Crew
    0.37
     Crews
    0.37
    Activations Density 0.000%

    No Known Activations