© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216321
    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_50_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
    Hak
    0.44
     hak
    0.42
    Eas
    0.41
    Կ
    0.41
     Glenn
    0.40
    Glenn
    0.40
    Hair
    0.40
    结局
    0.39
     씨
    0.39
     Hair
    0.38
    POSITIVE LOGITS
    illion
    0.41
    USION
    0.39
     psycho
    0.38
    zado
    0.38
    LLO
    0.37
    <0xA4>
    0.36
    ាំង
    0.36
    мою
    0.36
     monstrous
    0.35
    ভারে
    0.34
    Activations Density 0.000%

    No Known Activations