© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8820
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and related verbs

    oai_token-act-pair · gemini-2.0-flash

    "As we" intro paragraphs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    sidemargin
    -0.50
    ="//
    -0.50
    more
    -0.50
     more
    -0.47
    addCriterion
    -0.44
    ❋
    -0.44
    LookAnd
    -0.43
     AssemblyTitle
    -0.43
     More
    -0.43
     []:
    -0.43
    POSITIVE LOGITS
    RefNanny
    0.80
     Hongrie
    0.63
     ferdig
    0.61
    byes
    0.61
     виправивши
    0.59
     BorderRadius
    0.58
    pania
    0.56
     Shakspeare
    0.56
     نکنید
    0.56
    IsPostBack
    0.55
    Activations Density 2.987%

    No Known Activations