© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4083
    Prev
    Next
    INDEX
    Explanations

    text from a mathematics or physics paper

    oai_token-act-pair · gemini-2.0-flash

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AsUp
    -0.99
     متعلقه
    -0.88
    tanleria
    -0.86
    +#+#
    -0.85
    mass
    -0.83
    Mass
    -0.82
     HasFactory
    -0.81
    Numerology
    -0.79
     Reſ
    -0.79
     Mass
    -0.78
    POSITIVE LOGITS
     au
    0.47
     Sa
    0.44
    addPreferredGap
    0.42
     n
    0.42
     R
    0.42
     us
    0.40
     co
    0.40
    室
    0.38
     Tr
    0.37
    ix
    0.37
    Activations Density 1.443%

    No Known Activations