© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2791
    Prev
    Next
    INDEX
    Explanations

    marking or mark

    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_44_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
    erate
    0.38
    mun
    0.37
    醴
    0.37
    iamine
    0.36
     சிலையின்
    0.36
     பணிய
    0.35
     staw
    0.35
     досто
    0.35
    usste
    0.35
    𝗛
    0.35
    POSITIVE LOGITS
     marking
    1.72
     mark
    1.67
    marking
    1.61
     marked
    1.56
    mark
    1.55
     Marking
    1.53
    Mark
    1.52
    マーク
    1.43
    marked
    1.42
     Mark
    1.41
    Activations Density 0.182%

    No Known Activations