© 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. 687
    Prev
    Next
    INDEX
    Explanations

    a long quote mentioning Shakespeare's King Lear and the Globe Theater

    oai_token-act-pair · gemini-2.0-flash

    Archaic/formal language

    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
    indd
    -0.49
     continúas
    -0.42
    DataAnnotations
    -0.42
    NewGuid
    -0.36
    يميديا
    -0.35
    __":
    -0.34
     över
    -0.34
    ”,
    -0.32
    ilver
    -0.32
    CrossRef
    -0.32
    POSITIVE LOGITS
     pleaſure
    1.35
     Monfieur
    1.31
     myſelf
    1.28
     itſelf
    1.16
     purpoſe
    1.14
     houſe
    1.14
     Majefty
    1.13
     Theſe
    1.12
     raiſ
    1.11
     Houſe
    1.11
    Activations Density 1.057%

    No Known Activations