© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246604
    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_40_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
     protocolos
    0.44
    协议
    0.41
     মুঠ
    0.40
    Jan
    0.38
     protocolo
    0.38
     dhad
    0.38
    ៗ
    0.38
     protocols
    0.38
     Lern
    0.38
     phon
    0.37
    POSITIVE LOGITS
    直送
    0.39
    égalité
    0.37
    বেলা
    0.37
    垻
    0.37
     kick
    0.35
     pourquoi
    0.35
    有个
    0.35
     ativa
    0.35
     icon
    0.35
     electorate
    0.35
    Activations Density 0.000%

    No Known Activations