© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170012
    Prev
    Next
    INDEX
    Explanations

    man or management

    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_56_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
    M
    1.74
     M
    1.66
     М
    1.43
     ม
    1.42
    m
    1.39
    М
    1.37
     म
    1.35
     ম
    1.35
     મ
    1.30
     الم
    1.24
    POSITIVE LOGITS
    Mand
    0.49
    mand
    0.43
    mgmt
    0.38
     mant
    0.37
    Manifest
    0.35
     mand
    0.35
     Mand
    0.35
     والمر
    0.34
     mandrel
    0.34
    Mant
    0.34
    Activations Density 0.003%

    No Known Activations