© 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. 4226
    Prev
    Next
    INDEX
    Explanations

    the words "lot" or "lots", sometimes in conjunction with numbers or verbs

    oai_token-act-pair · gemini-2.0-flash

    lots

    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
    <bos>
    -0.75
     viață
    -0.65
     demais
    -0.65
     wikipagina
    -0.63
    tagHelperRunner
    -0.62
     creș
    -0.62
     bebê
    -0.61
     ubicada
    -0.60
     sucedió
    -0.60
     sympathize
    -0.59
    POSITIVE LOGITS
    UIControlState
    0.80
    personalised
    0.69
    ISATION
    0.68
    BorderFactory
    0.67
    .(*
    0.65
    .[/
    0.65
    labour
    0.65
     standardised
    0.63
    WEBPACK
    0.63
    URIComponent
    0.63
    Activations Density 0.945%

    No Known Activations