© 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. 11518
    Prev
    Next
    INDEX
    Explanations

    phrases describing a positive or supportive experience involving people and a higher power

    oai_token-act-pair · gemini-2.0-flash

    technical jargon and functions

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

    Positive sentiment

    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
     told
    -0.80
     advised
    -0.78
     asked
    -0.72
     reminded
    -0.72
     encouraged
    -0.69
    ########.
    -0.65
     allowed
    -0.65
     slapped
    -0.61
    endpush
    -0.60
     instructed
    -0.60
    POSITIVE LOGITS
    UnknownFields
    0.70
    ReusableCell
    0.61
    setVerticalGroup
    0.57
    theoremstyle
    0.52
    lá
    0.52
     there
    0.51
    UTERS
    0.51
    ItemBackground
    0.50
     Revue
    0.50
    undle
    0.50
    Activations Density 1.258%

    No Known Activations