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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10325
    Prev
    Next
    INDEX
    Explanations

    the phrase "kind of" or "kinds of"

    oai_token-act-pair · gemini-2.0-flash

    kind/kinds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     betweenstory
    -0.76
     AssemblyTitle
    -0.58
    脚注の使い方
    -0.57
    astéroïdes
    -0.56
     nahilalakip
    -0.52
     esternos
    -0.51
    $_['
    -0.50
    amom
    -0.50
    iseksi
    -0.50
    原始内容存档于
    -0.49
    POSITIVE LOGITS
    endforeach
    0.53
    optarg
    0.48
    RenderAtEndOf
    0.47
    endwhile
    0.46
     home
    0.46
    badlogic
    0.45
    ignment
    0.45
    ngOnInit
    0.45
     overlapping
    0.44
    tableFuture
    0.44
    Activations Density 0.977%

    No Known Activations