© 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. 3052
    Prev
    Next
    INDEX
    Explanations

    the syntax of programming code in various languages like C#, PHP, javascript and others.

    oai_token-act-pair · gemini-2.0-flash

    words related to coding frameworks and libraries

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

    code snippets

    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
    __(/*!
    -0.50
     metaphor
    -0.48
     context
    -0.48
    Ctx
    -0.48
    loroethane
    -0.48
    zenberg
    -0.47
    LookAnd
    -0.46
     ear
    -0.45
     pot
    -0.45
    syms
    -0.45
    POSITIVE LOGITS
    quelize
    0.61
    URLException
    0.58
    FormTagHelper
    0.57
     CWE
    0.57
    mybatisplus
    0.57
    })`
    0.54
    bootstrapcdn
    0.53
    SFD
    0.52
    AutoField
    0.52
    GEBURTS
    0.50
    Activations Density 2.691%

    No Known Activations