© 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. 32059
    Prev
    Next
    INDEX
    Explanations

    Pyramid

    np_max-act-logits · gemini-2.5-flash-lite
    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
     heights
    0.40
    <unused68>
    0.39
    Heights
    0.39
    邱
    0.38
     HEIGHT
    0.38
    Hi
    0.37
    ]))
    0.37
     Hi
    0.36
    Hö
    0.36
    hou
    0.36
    POSITIVE LOGITS
     polarised
    0.43
    یں۔
    0.42
     Taz
    0.42
     Gazetteer
    0.40
    장이
    0.39
    쑹
    0.39
     按
    0.38
    ôn
    0.38
    りが
    0.38
     Arms
    0.38
    Activations Density 0.003%

    No Known Activations