© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235500
    Prev
    Next
    INDEX
    Explanations

    magnetism properties

    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_46_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
     R
    0.43
     proguard
    0.40
     П
    0.38
    芭
    0.38
    ခြေ
    0.38
    TOOLBAR
    0.37
    chronic
    0.37
    ന്‍
    0.36
    R
    0.36
     correctes
    0.36
    POSITIVE LOGITS
     mon
    0.42
     micros
    0.41
     Micros
    0.39
    kau
    0.38
     roh
    0.38
     monos
    0.38
    Hand
    0.37
    ophy
    0.37
     Kurz
    0.37
    }],
    0.37
    Activations Density 0.000%

    No Known Activations