© 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. 6273
    Prev
    Next
    INDEX
    Explanations

    snippets of text describing types of people.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'person'

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

    people

    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
    GraphicsUnit
    -0.64
    发表于
    -0.55
    🏻
    -0.51
     geste
    -0.48
    🏼
    -0.47
     cref
    -0.46
    ControllerAdvice
    -0.45
    $_['
    -0.44
    󠁢
    -0.44
     []:
    -0.44
    POSITIVE LOGITS
     people
    1.34
     person
    1.23
    people
    1.11
     personne
    1.06
     persons
    1.06
    Person
    1.00
    person
    1.00
     PERSON
    1.00
     personnes
    0.98
     somebody
    0.97
    Activations Density 1.198%

    No Known Activations