© 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. 16145
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    th

    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
    alité
    -0.60
     Audiodateien
    -0.58
    WebControls
    -0.58
    "]));
    -0.57
     bandages
    -0.57
    >>();
    -0.55
    __((
    -0.55
    Биография
    -0.54
    AccessFile
    -0.54
    NameInMap
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.57
     vaisseaux
    0.56
     quelcon
    0.54
     exemplaires
    0.53
     prêtres
    0.52
     lèvres
    0.52
     vœux
    0.50
     dégâts
    0.50
     avoient
    0.50
     enfans
    0.49
    Activations Density 3.565%

    No Known Activations