Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16373
    Prev
    Next
    INDEX
    Explanations

    customer reviews, especially when enthusiastic

    oai_token-act-pair · gemini-2.0-flash

    mixed snippets of text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    melidir
    -0.42
    mr
    -0.41
     bosques
    -0.40
    stdarg
    -0.39
     지
    -0.39
     trou
    -0.37
    мер
    -0.36
    beforeSend
    -0.36
    χη
    -0.35
    voja
    -0.35
    POSITIVE LOGITS
    NameInMap
    0.90
     createState
    0.82
    ########.
    0.79
     BoxFit
    0.77
    oa̍t
    0.73
    writeFieldEnd
    0.73
    IonicModule
    0.71
     NSCoder
    0.71
    IBar
    0.71
    malink
    0.71
    Activations Density 1.387%

    No Known Activations