© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141860
    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_12_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
    करणा
    0.58
     شہریوں
    0.54
    ktion
    0.52
    profitable
    0.52
    ᱖
    0.51
    associazione
    0.48
     ఒకటి
    0.48
    ICHIGAN
    0.47
     feitas
    0.47
    ilane
    0.47
    POSITIVE LOGITS
     freezer
    0.63
     geology
    0.63
     mother
    0.62
     they
    0.58
     -=
    0.57
     romper
    0.56
     corrupt
    0.55
     word
    0.54
     language
    0.54
     she
    0.54
    Activations Density 0.000%

    No Known Activations