© 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. 8365
    Prev
    Next
    INDEX
    Explanations

    articles, possessives, and words that suggest the sentence is elaborating on information

    oai_token-act-pair · gemini-2.0-flash

    young

    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
    rénées
    -0.68
     '{@
    -0.63
    ,‎
    -0.62
     OnInit
    -0.61
    awtextra
    -0.59
     Stoppers
    -0.59
    nonatomic
    -0.59
    曖昧さ回避
    -0.58
    ughty
    -0.58
     onStop
    -0.57
    POSITIVE LOGITS
     young
    2.20
    young
    1.75
    Young
    1.63
     YOUNG
    1.59
     Young
    1.53
     jungen
    1.49
     junge
    1.48
     jeune
    1.47
    YOUNG
    1.39
     jonge
    1.33
    Activations Density 2.629%

    No Known Activations