© 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. 6243
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns, conjunctions, and verbs.

    oai_token-act-pair · gemini-2.0-flash

    presence of the word "I"

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

    I

    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
    NewUrlParser
    -0.66
     FetchType
    -0.58
     createState
    -0.55
     thon
    -0.55
    पया
    -0.54
     springfox
    -0.53
    ksesta
    -0.52
     (++
    -0.50
    ónimos
    -0.50
     _('
    -0.50
    POSITIVE LOGITS
     just
    0.84
    just
    0.71
    Just
    0.68
     Just
    0.68
     JUST
    0.59
     its
    0.55
     Its
    0.52
    Its
    0.52
    enumi
    0.52
     ddelweddau
    0.50
    Activations Density 0.595%

    No Known Activations