© 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. 14557
    Prev
    Next
    INDEX
    Explanations

    phrases ending with a period or quotation mark and sometimes an preceding comma

    oai_token-act-pair · gemini-2.0-flash

    quote

    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
    ”.
    -1.09
    ’.
    -0.92
    FieldNumber
    -0.90
    RegressionTest
    -0.89
     tartalomajánló
    -0.84
    ``.
    -0.84
    "];
    -0.82
    behörde
    -0.81
    ».
    -0.80
    ".
    -0.80
    POSITIVE LOGITS
     ་་
    0.90
    "
    0.69
    <em>
    0.68
     ―――――
    0.66
     Sarm
    0.62
     "¿
    0.62
    ,'"
    0.59
    ,"
    0.59
    </em>
    0.55
    "¿
    0.51
    Activations Density 2.325%

    No Known Activations