© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13734
    Prev
    Next
    INDEX
    Explanations

    code snippets, often C-like loops using `i`, `n`, `x`, `v`, or `l` as variables

    oai_token-act-pair · gemini-2.0-flash

    i

    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
     "..\..\
    -0.83
     resourceCulture
    -0.79
     "..\..\..\
    -0.72
    SourceChecksum
    -0.67
     betweenstory
    -0.65
    Personendaten
    -0.65
    TProtocol
    -0.64
     noDo
    -0.62
    makeConstraints
    -0.61
    /**
    -0.61
    POSITIVE LOGITS
    hed
    0.50
    vens
    0.49
     hem
    0.49
     Mo
    0.48
     *_
    0.47
    aser
    0.47
    het
    0.46
    hrt
    0.46
    ethe
    0.45
     het
    0.45
    Activations Density 13.735%

    No Known Activations