© 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. 12955
    Prev
    Next
    INDEX
    Explanations

    phrases containing "that" and/or "one".

    oai_token-act-pair · gemini-2.0-flash

    Descriptive/Formal text

    np_max-act · 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
     betweenstory
    -0.71
    Cyfeiriadau
    -0.54
     fubject
    -0.54
     Mercurio
    -0.53
     Goldie
    -0.52
    LookAnd
    -0.52
    DebuggerStep
    -0.51
    guió
    -0.51
     Hym
    -0.51
     Richelieu
    -0.50
    POSITIVE LOGITS
    awtextra
    0.72
    kloped
    0.71
    GraphicsUnit
    0.69
    ⓧ
    0.62
     onAnimation
    0.57
    EDEFAULT
    0.53
    rawDesc
    0.52
    IBar
    0.52
    github
    0.52
     GoogleFonts
    0.51
    Activations Density 2.946%

    No Known Activations