© 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. 4476
    Prev
    Next
    INDEX
    Explanations

    technical vocabularly used in scientific papers, and also finds attempts to quantify information

    oai_token-act-pair · gemini-2.0-flash

    Repeated letters

    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
    OGND
    -0.84
    ftagPool
    -0.78
    AndEndTag
    -0.72
     unknownFields
    -0.70
     Glaser
    -0.66
    发表于
    -0.65
    MigrationBuilder
    -0.64
    oredCriteria
    -0.63
     Kaufman
    -0.61
    ⓧ
    -0.61
    POSITIVE LOGITS
     PP
    1.02
     SS
    0.94
     PPP
    0.89
     CC
    0.89
     DD
    0.88
     NN
    0.87
     CCC
    0.87
     SSS
    0.85
     BB
    0.85
     RR
    0.84
    Activations Density 12.658%

    No Known Activations