© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 251188
    Prev
    Next
    INDEX
    Explanations

    let's figure out

    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
     зу
    0.41
     rozs
    0.40
    备
    0.39
    别
    0.38
    Roz
    0.38
     roz
    0.37
    hive
    0.37
    yat
    0.37
     فط
    0.36
     쇼
    0.36
    POSITIVE LOGITS
    ansa
    0.38
     ideologies
    0.38
    संर
    0.38
     collaborating
    0.37
    unnels
    0.37
    риди
    0.37
     screaming
    0.37
     সং
    0.36
    frig
    0.36
     blender
    0.36
    Activations Density 0.000%

    No Known Activations