© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4975
    Prev
    Next
    INDEX
    Explanations

    how to positively parent a child whose behavior needs correcting

    oai_token-act-pair · gemini-2.0-flash

    Interpersonal communication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MotionEvent
    -0.65
     betweenstory
    -0.63
    CppCodeGen
    -0.56
     resourceCulture
    -0.55
    Chham
    -0.54
    WriteTagHelper
    -0.51
     TextAppearance
    -0.51
    LETE
    -0.49
     MenuView
    -0.48
    endpush
    -0.47
    POSITIVE LOGITS
     honor
    0.62
     الحره
    0.62
     show
    0.56
    yntaxException
    0.53
     quæ
    0.52
     Caballero
    0.52
     honour
    0.51
     validating
    0.50
    แก่
    0.49
     AssemblyTitle
    0.49
    Activations Density 5.239%

    No Known Activations