© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13632
    Prev
    Next
    INDEX
    Explanations

    words related to uniqueness and identification, especially in the context of devices and systems

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers and properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     unique
    -3.11
    unique
    -2.97
     Unique
    -2.89
    Unique
    -2.88
     UNIQUE
    -2.50
     uniques
    -2.33
     uniquely
    -2.22
     uniqueness
    -2.19
    UNIQUE
    -2.19
     unieke
    -2.13
    POSITIVE LOGITS
    ArgsConstructor
    0.63
    CloseOperation
    0.63
    netinet
    0.57
    ellschaft
    0.56
    fromnode
    0.56
     hæ
    0.54
    cstdlib
    0.54
    TagHelpers
    0.53
    cassert
    0.52
    enegro
    0.52
    Activations Density 1.766%

    No Known Activations