© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6176
    Prev
    Next
    INDEX
    Explanations

    sentences about rules or requirements using the words "must," "should," and "to be".

    oai_token-act-pair · gemini-2.0-flash

    programming keywords and conventions

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

    rule specifications

    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
     does
    -0.92
    does
    -0.73
     is
    -0.72
     doesn
    -0.63
     did
    -0.59
     makes
    -0.59
     Does
    -0.58
     finds
    -0.57
     takes
    -0.56
     works
    -0.56
    POSITIVE LOGITS
     ModelExpression
    0.73
     onCancelled
    0.63
    complexContent
    0.63
     <<<<<<<<<<<<<<
    0.62
    AndEndTag
    0.62
    ArgsConstructor
    0.62
     '\\;'
    0.62
     AssemblyCulture
    0.61
    +#+#
    0.61
     ComVisible
    0.60
    Activations Density 1.439%

    No Known Activations