© 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. 4565
    Prev
    Next
    INDEX
    Explanations

    the word 'articles' and sometimes also 'papers', especially in a research context

    oai_token-act-pair · gemini-2.0-flash

    articles

    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
    2
    -0.74
    I
    -0.65
    ing
    -0.64
    4
    -0.63
    H
    -0.59
    0
    -0.58
    all
    -0.57
    1
    -0.57
    ous
    -0.56
    6
    -0.56
    POSITIVE LOGITS
    %)$
    0.91
    %")
    0.91
    athread
    0.90
    =")
    0.88
    "])
    0.87
    FTFY
    0.86
    --)
    0.85
    ,:);
    0.84
    ++
    0.84
    ]")
    0.83
    Activations Density 1.829%

    No Known Activations