© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7641
    Prev
    Next
    INDEX
    Explanations

    the word "Great"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'great'

    np_token-act-pair-logits · gpt-4o-mini

    Great

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Anat
    -0.56
     loudest
    -0.55
     harps
    -0.54
     bilingual
    -0.54
     Crank
    -0.53
     innermost
    -0.53
     LSA
    -0.53
     onsite
    -0.53
     Bessel
    -0.53
     therein
    -0.52
    POSITIVE LOGITS
    ExecuteReader
    0.66
    IsPostBack
    0.64
    migrationBuilder
    0.60
     @"/
    0.57
     MainAxisSize
    0.57
     Exactos
    0.56
    MemoryWarning
    0.56
     CreateTagHelper
    0.56
    onOptions
    0.55
     Италијани
    0.54
    Activations Density 0.404%

    No Known Activations