© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11286
    Prev
    Next
    INDEX
    Explanations

    jargon related to technical, research, medical, or business fields

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Monfieur
    -0.34
     Efq
    -0.30
     raiſ
    -0.26
     whoſe
    -0.24
     againſt
    -0.24
     myſelf
    -0.24
     bogotá
    -0.24
    <bos>
    -0.24
     ſeveral
    -0.23
    sprzedam
    -0.23
    POSITIVE LOGITS
     Vikipedi
    0.22
    ]='\
    0.22
    .
    0.19
    defined
    0.19
    clearly
    0.19
     nog
    0.19
    for
    0.18
    first
    0.18
    still
    0.18
    </h4>
    0.18
    Activations Density 28.954%

    No Known Activations