© 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. 13920
    Prev
    Next
    INDEX
    Explanations

    code snippets from various languages and related identifiers and keywords

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
     BoxDecoration
    -0.58
    ngdoc
    -0.57
    __(/*!
    -0.55
    RectangleBorder
    -0.52
    rounder
    -0.52
    NavController
    -0.51
    _))
    -0.51
    存于互联网档案馆
    -0.50
     kür
    -0.50
    RouterModule
    -0.50
    POSITIVE LOGITS
    Przypisy
    0.65
    :✨
    0.63
    حوالہ
    0.59
    WebVitals
    0.56
    Jegyzetek
    0.56
    expandindo
    0.52
    脚注の使い方
    0.51
     gynhyrchwyd
    0.50
     Италијани
    0.49
     يتيمه
    0.49
    Activations Density 0.729%

    No Known Activations