© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13423
    Prev
    Next
    INDEX
    Explanations

    personal service oriented marketing language like "we", "our", and "I"

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or terms

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

    business descriptions

    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
     intending
    -0.50
    might
    -0.48
    Hundred
    -0.44
    ioutil
    -0.44
     Morton
    -0.44
    thousands
    -0.44
    UATION
    -0.44
    Loved
    -0.43
    pinas
    -0.43
    onicus
    -0.43
    POSITIVE LOGITS
     виправивши
    0.75
     surla
    0.66
    DoubleQuotes
    0.65
    Према
    0.65
    tagHelperRunner
    0.60
    DebuggerNonUser
    0.59
    TestingModule
    0.56
    CopyWith
    0.54
    ViewFeatures
    0.54
     tilbud
    0.54
    Activations Density 1.593%

    No Known Activations