© 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. 10668
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation marks, short words, and sentence fragments often preceded or followed by periods or blank lines.

    oai_token-act-pair · gemini-2.0-flash

    Marketing and advertising

    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
    Билгалдахарш
    -1.56
    tagHelperRunner
    -1.53
     resourceCulture
    -1.47
     EconPapers
    -1.41
     Савезне
    -1.33
    featureID
    -1.28
     виправивши
    -1.20
    StructEnd
    -1.20
     AssemblyCulture
    -1.20
     disambiguazione
    -1.19
    POSITIVE LOGITS
     even
    0.90
     
    0.79
     with
    0.74
     in
    0.72
     Even
    0.68
    even
    0.68
     no
    0.66
     "
    0.65
    Even
    0.65
     is
    0.65
    Activations Density 4.969%

    No Known Activations