© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7527
    Prev
    Next
    INDEX
    Explanations

    various types of punctuation and formatting, including bullet points, subscripts, superscripts and trademark symbols

    oai_token-act-pair · gemini-2.0-flash

    Special characters/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    XmlAccessType
    -0.66
    UnitTesting
    -0.60
    esse
    -0.55
    reportWebVitals
    -0.53
     CreateTagHelper
    -0.53
    principalTable
    -0.53
     &___
    -0.52
    WebElementEntity
    -0.49
    Composable
    -0.48
    __(/*!
    -0.48
    POSITIVE LOGITS
    <bos>
    2.25
     the
    0.52
     you
    0.52
    __':
    0.47
    Fun
    0.47
     to
    0.46
    #
    0.45
     access
    0.45
     Verfügung
    0.45
     experience
    0.45
    Activations Density 3.282%

    No Known Activations