© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170229
    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_56_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
     MAKING
    0.42
    ]][
    0.41
     Making
    0.37
     Brack
    0.35
     অফ
    0.35
     Turnbull
    0.34
    最后一
    0.34
     вели
    0.33
    ]-\
    0.33
    வுகளில்
    0.33
    POSITIVE LOGITS
     child
    0.54
    child
    0.51
     person
    0.45
    される
    0.45
     menino
    0.44
     dítě
    0.44
     enfant
    0.43
     criança
    0.43
     kid
    0.42
     }^{*}$
    0.42
    Activations Density 0.000%

    No Known Activations