© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198378
    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_27_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
    Starburst
    0.44
    ולנד
    0.44
    ouvrir
    0.41
     Київ
    0.39
    咽
    0.38
    кры
    0.38
    Merhaba
    0.38
     vrijdag
    0.38
    їн
    0.38
     deputado
    0.37
    POSITIVE LOGITS
     Therefore
    0.40
     Consequently
    0.37
     consequently
    0.36
     remaining
    0.36
     probably
    0.35
     worlds
    0.35
     „
    0.34
     จึง
    0.34
     Probably
    0.34
     Taking
    0.34
    Activations Density 0.000%

    No Known Activations