© 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. 8614
    Prev
    Next
    INDEX
    Explanations

    words related to accounting services

    oai_token-act-pair · gemini-2.0-flash

    programming or technical terms

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

    Code-related terms

    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
     дописавши
    -0.74
     ExecuteAsync
    -0.67
    :✨
    -0.63
    homonymie
    -0.61
    #+#
    -0.60
    FOOTNOTES
    -0.56
     RIPRODUZIONE
    -0.55
     dAtA
    -0.53
     rând
    -0.52
    featureID
    -0.51
    POSITIVE LOGITS
    RunAsync
    0.59
    BuildConfig
    0.59
    TabIndex
    0.55
     BrowserModule
    0.53
     InputDecoration
    0.52
    脚注の使い方
    0.51
     lett
    0.51
     recensement
    0.50
    letta
    0.49
    TemporalType
    0.49
    Activations Density 1.829%

    No Known Activations