© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11881
    Prev
    Next
    INDEX
    Explanations

    the verb 'to have' in various forms, sometimes near locations

    oai_token-act-pair · gemini-2.0-flash

    has/have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    principalTable
    -0.67
    μφωνα
    -0.67
     wikipagina
    -0.56
    SAFE
    -0.54
    Safe
    -0.53
    naldo
    -0.50
    }{*}{}
    -0.50
     yana
    -0.50
     địa
    -0.50
    kaido
    -0.49
    POSITIVE LOGITS
    ValueStyle
    0.57
    pektrum
    0.52
     recognised
    0.51
     Majest
    0.51
     interviewed
    0.51
     listed
    0.50
     Quoted
    0.49
     '\\;'
    0.49
     pegged
    0.48
     named
    0.46
    Activations Density 1.656%

    No Known Activations