© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14819
    Prev
    Next
    INDEX
    Explanations

    a variety of contextually different terms, including some medical research terms, but a unifying characteristic is not obvious to deduce

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    RenderAtEndOf
    -1.02
    GOTREF
    -0.88
     <<<<<<<<<<<<<<
    -0.84
     NSCoder
    -0.84
    migrationBuilder
    -0.82
    ValueGeneration
    -0.80
    complexContent
    -0.80
    原始内容存档于
    -0.79
    (!__
    -0.76
    Hentet
    -0.75
    POSITIVE LOGITS
    oas
    0.44
    NSON
    0.42
    <bos>
    0.41
    dfa
    0.39
    bono
    0.35
     acceptez
    0.35
    execSQL
    0.34
    halts
    0.34
    Head
    0.34
    ślę
    0.33
    Activations Density 8.738%

    No Known Activations