© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12428
    Prev
    Next
    INDEX
    Explanations

    the ending of sentences and lists of authors

    oai_token-act-pair · gemini-2.0-flash

    period character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Portály
    -0.66
     nakalista
    -0.63
    发表于
    -0.60
    MemoryWarning
    -0.59
    eqn
    -0.59
    tvguidetime
    -0.59
    ffindor
    -0.59
    最快更新
    -0.59
     AssemblyCulture
    -0.58
    LLocation
    -0.54
    POSITIVE LOGITS
    <bos>
    0.66
    rungsseite
    0.54
     desecha
    0.49
    };*/
    0.47
     voer
    0.44
     démarche
    0.44
    San
    0.44
     trânsito
    0.44
    /*
    0.43
     leitura
    0.43
    Activations Density 0.946%

    No Known Activations