© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5517
    Prev
    Next
    INDEX
    Explanations

    words that describe a person and associated attributes in a formal setting like a news report or query

    oai_token-act-pair · gemini-2.0-flash

    is

    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
     EconPapers
    -0.99
    StoryboardSegue
    -0.91
    setVerticalGroup
    -0.81
    
    -0.79
    ConstraintMaker
    -0.69
     AttributeSet
    -0.68
     дописавши
    -0.66
     CURIAM
    -0.61
    fjspx
    -0.61
    >-->
    -0.60
    POSITIVE LOGITS
     is
    1.31
     are
    1.08
    are
    0.72
     Are
    0.69
     está
    0.69
     están
    0.65
     estamos
    0.64
     Is
    0.64
     estoy
    0.63
     estás
    0.62
    Activations Density 3.424%

    No Known Activations