© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51130
    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_30_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
     Ahmedabad
    0.40
    security
    0.39
     she
    0.38
    als
    0.37
    ᗩ
    0.36
     studente
    0.36
    測
    0.35
    wares
    0.35
    rating
    0.35
    template
    0.34
    POSITIVE LOGITS
     mysticism
    0.38
    کین
    0.38
    慜
    0.37
     revisiting
    0.37
    вя
    0.36
     predation
    0.36
     лам
    0.35
     Candida
    0.35
     indexOf
    0.34
    保养
    0.34
    Activations Density 0.000%

    No Known Activations