© 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. 16353
    Prev
    Next
    INDEX
    Explanations

    pronouns used in narratives/stories, often combined with auxiliary or modal verbs

    oai_token-act-pair · gemini-2.0-flash

    looked

    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
    findpost
    -0.94
    GraphicsUnit
    -0.90
     feel
    -0.87
    ftagPool
    -0.87
    LabelTagHelper
    -0.85
     defaultstate
    -0.84
     незавершена
    -0.82
    ArrowToggle
    -0.82
     AssemblyCulture
    -0.81
    ########.
    -0.81
    POSITIVE LOGITS
     looked
    0.81
    looked
    0.55
    pau
    0.50
     Looked
    0.50
     ausz
    0.49
    छ
    0.48
    〃
    0.43
     Führung
    0.42
    orca
    0.41
     uitz
    0.40
    Activations Density 2.880%

    No Known Activations