© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3552
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating insincere or incomplete actions

    oai_token-act-pair · gemini-2.0-flash

    Incomplete or dismissive actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     deliberately
    -0.52
     intentional
    -0.50
     deliberate
    -0.50
    gorm
    -0.49
     purposefully
    -0.46
    extAlignment
    -0.44
     purposely
    -0.43
     bewusst
    -0.42
    ))^
    -0.42
     purposeful
    -0.41
    POSITIVE LOGITS
    NameInMap
    0.91
     jScrollPane
    0.80
    +#+#
    0.76
    tagHelperRunner
    0.72
    fjspx
    0.69
    SourceChecksum
    0.69
    abstractmethod
    0.69
    ]")]
    0.65
    ViewImports
    0.65
    ########.
    0.63
    Activations Density 1.547%

    No Known Activations