© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13939
    Prev
    Next
    INDEX
    Explanations

    closing curly brackets with leading spaces and newlines, often followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    closing braces in code

    np_token-act-pair-logits · gpt-4o-mini

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Sarm
    -0.59
    DockStyle
    -0.59
    rabaya
    -0.55
     Volga
    -0.54
    elemField
    -0.54
    Discografia
    -0.53
    inheritDoc
    -0.52
     indemnity
    -0.51
     Herod
    -0.50
    nodoc
    -0.50
    POSITIVE LOGITS
    ↵
    0.76
    ReusableCell
    0.66
    setDo
    0.47
    ">//
    0.46
    ilación
    0.45
    
    0.43
    Mek
    0.43
    drawSprites
    0.43
    これも
    0.42
    ToScroll
    0.42
    Activations Density 0.133%

    No Known Activations