© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6084
    Prev
    Next
    INDEX
    Explanations

    the word boundary

    oai_token-act-pair · gemini-2.0-flash

    boundary

    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
     Zacks
    -0.63
    TextWatcher
    -0.61
     of
    -0.61
     跳转至
    -0.60
    ंदीखरीदारी
    -0.59
     more
    -0.52
    MessageOf
    -0.52
    +:+
    -0.51
    forRoot
    -0.51
    FormBorderStyle
    -0.50
    POSITIVE LOGITS
    ])));
    0.76
    phazard
    0.72
    omitempty
    0.72
    ormick
    0.71
    EDEFAULT
    0.68
    edicated
    0.68
    =?";
    0.67
    ürlich
    0.67
    __).
    0.67
    acherous
    0.66
    Activations Density 2.455%

    No Known Activations