© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4785
    Prev
    Next
    INDEX
    Explanations

    the word "and," sometimes in combination with other nearby words

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     transfieras
    -0.90
    CloseOperation
    -0.88
    parsedMessage
    -0.77
    exitRule
    -0.70
    UserScript
    -0.68
    KURZBESCHREIBUNG
    -0.66
    basicConfig
    -0.66
    enumi
    -0.65
     EClass
    -0.64
    IntoConstraints
    -0.64
    POSITIVE LOGITS
     respective
    0.66
     subdivided
    0.61
     respectively
    0.61
     '.';
    0.57
     Woolf
    0.56
     utilised
    0.56
     Duque
    0.55
     '-';
    0.55
    ctiveness
    0.54
     utilized
    0.54
    Activations Density 1.276%

    No Known Activations