© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10063
    Prev
    Next
    INDEX
    Explanations

    HTML code relating to file references and citations

    oai_token-act-pair · gemini-2.0-flash

    cite, rel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    InputBorder
    -0.76
     pinulongan
    -0.71
     réfugiés
    -0.67
    SequentialGroup
    -0.66
    igshid
    -0.65
    ImageContext
    -0.65
    esModule
    -0.63
    aneta
    -0.63
    WarningLevel
    -0.63
    ChildIndex
    -0.62
    POSITIVE LOGITS
    <bos>
    1.54
    ’
    0.54
    The
    0.53
    I
    0.51
    ↵
    0.50
    It
    0.49
    '
    0.49
    ‘
    0.48
    This
    0.47
    [toxicity=0]
    0.46
    Activations Density 0.156%

    No Known Activations