© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10020
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or expressions

    oai_token-act-pair · gemini-2.0-flash

    Left and Right

    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
     endforeach
    -0.44
     ?>>
    -0.44
     ​​
    -0.41
     تانيه
    -0.40
     klap
    -0.40
     iArr
    -0.40
    рыя
    -0.39
     Abad
    -0.38
     endblock
    -0.38
    alat
    -0.37
    POSITIVE LOGITS
    left
    1.75
     left
    1.38
    langle
    1.06
     Left
    1.06
    right
    1.00
     LEFT
    0.97
     izquierda
    0.94
    LEFT
    0.91
    rangle
    0.87
    Left
    0.85
    Activations Density 1.106%

    No Known Activations