© 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. 9161
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code snippets

    oai_token-act-pair · gemini-2.0-flash

    say mathematical symbols

    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
     sense
    -1.63
    sense
    -1.30
     Sense
    -1.12
    Sense
    -1.10
     SENSE
    -1.09
     sentido
    -0.97
     senso
    -0.81
     senses
    -0.79
     sens
    -0.74
    ense
    -0.73
    POSITIVE LOGITS
     fubject
    0.90
    tagHelperRunner
    0.89
     oprot
    0.88
     myſelf
    0.84
     itſelf
    0.82
     ſeveral
    0.80
     ―――――
    0.79
     saites
    0.79
     ſtate
    0.79
    migrationBuilder
    0.79
    Activations Density 2.753%

    No Known Activations