© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65477
    Prev
    Next
    INDEX
    Explanations

    content

    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
     perpetuate
    0.42
    radical
    0.40
     incompat
    0.39
     hợp
    0.39
     Compatibility
    0.39
     compatibility
    0.39
     далі
    0.38
    搖
    0.38
    eneral
    0.38
    RUB
    0.38
    POSITIVE LOGITS
    absolutely
    0.46
    breaks
    0.43
     certainly
    0.41
     absolutely
    0.41
    "]))
    0.41
     certamente
    0.40
     breaching
    0.40
    "])
    0.40
    很
    0.39
     sehr
    0.38
    Activations Density 0.006%

    No Known Activations