© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14036
    Prev
    Next
    INDEX
    Explanations

    what looks like Twitter usernames or academic references

    oai_token-act-pair · gemini-2.0-flash

    online conversations/mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ansh
    -0.56
     كورة
    -0.56
    XmlType
    -0.56
     protoimpl
    -0.54
    あく
    -0.54
    Viitteet
    -0.54
    dafx
    -0.54
     ích
    -0.54
    Доро
    -0.53
    Filmografia
    -0.53
    POSITIVE LOGITS
    Vidite
    0.67
    CloseOperation
    0.53
    extAlignment
    0.49
    makeText
    0.48
    ornis
    0.47
    }]
    0.46
    NgModule
    0.46
    uset
    0.46
    UnitTesting
    0.45
    Flop
    0.45
    Activations Density 1.382%

    No Known Activations