© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62432
    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_11_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
     آ
    0.48
     sovereignty
    0.47
    يل
    0.46
    JL
    0.46
     à
    0.46
     Projection
    0.46
    垂
    0.45
    gling
    0.44
     місто
    0.44
    PHIA
    0.43
    POSITIVE LOGITS
     несмотря
    0.48
    炷
    0.48
     amarilla
    0.45
    ியில்
    0.45
     tentunya
    0.45
     большая
    0.45
     기름
    0.44
    вым
    0.44
     yeast
    0.44
    ักษณะ
    0.44
    Activations Density 0.000%

    No Known Activations