© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1859
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    Code and hexadecimals

    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
    AMPTON
    -0.47
    ape
    -0.44
     Eink
    -0.44
     irm
    -0.44
     acu
    -0.43
    ITOS
    -0.43
    enterio
    -0.43
     haute
    -0.42
    aire
    -0.41
    neous
    -0.41
    POSITIVE LOGITS
    WriteBarrier
    0.81
     giusti
    0.79
     morire
    0.77
     stället
    0.77
     colorés
    0.75
     precedenti
    0.73
     illustrazione
    0.73
     nemici
    0.73
     vantaggio
    0.73
     précédents
    0.72
    Activations Density 19.400%

    No Known Activations