© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    fragments of jQuery code

    oai_token-act-pair · gemini-2.0-flash

    jQuery syntax and attributes

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

    Punctuation

    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
    WithIOException
    -0.83
    LookAnd
    -0.81
    Personendaten
    -0.74
     صوتيه
    -0.73
    elemField
    -0.72
    spender
    -0.71
     ProtoMessage
    -0.69
    styleType
    -0.69
     resourceCulture
    -0.68
     Савезне
    -0.68
    POSITIVE LOGITS
    adal
    0.46
    omie
    0.42
    UVWXYZ
    0.39
    上
    0.39
    be
    0.39
    textwidth
    0.39
    abr
    0.38
     ++)
    0.38
    gnu
    0.37
     Jule
    0.37
    Activations Density 0.198%

    No Known Activations