© 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. 12461
    Prev
    Next
    INDEX
    Explanations

    periods and topic-ending punctuation, sometimes activating on numbers and a few relevant nouns

    oai_token-act-pair · gemini-2.0-flash

    periods

    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
    ↵↵
    -0.69
    .
    -0.52
    ”.
    -0.49
    -/
    -0.46
     acceptor
    -0.45
    -.
    -0.45
    Бележки
    -0.45
     buch
    -0.44
    ọt
    -0.44
    ('=
    -0.44
    POSITIVE LOGITS
    istoitu
    0.91
     ujednoznacz
    0.90
    ValueStyle
    0.83
     ExecuteAsync
    0.82
     disambiguazione
    0.82
    Datuak
    0.80
    ContentAsync
    0.76
     يتيمه
    0.76
    __':
    0.74
    SequentialGroup
    0.73
    Activations Density 3.206%

    No Known Activations