© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12966
    Prev
    Next
    INDEX
    Explanations

    legal terms, especially related to sentencing.

    oai_token-act-pair · gemini-2.0-flash

    Legal/medical/governmental topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     mate
    -0.47
     mates
    -0.45
    SpringRunner
    -0.44
     Sagar
    -0.43
    se
    -0.43
    ersk
    -0.43
    .*")]
    -0.43
    INSEE
    -0.41
    Cuisine
    -0.41
     cop
    -0.41
    POSITIVE LOGITS
    +#+#
    0.83
     démocr
    0.82
     avoient
    0.74
    CppMethod
    0.71
     resourceCulture
    0.69
     Efq
    0.69
     quæ
    0.69
     كومونز
    0.68
     Eſ
    0.68
     étoient
    0.67
    Activations Density 2.305%

    No Known Activations