© 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. 8901
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, colons, and words related to sports teams or leagues.

    oai_token-act-pair · gemini-2.0-flash

    dated news

    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
    hematical
    -0.53
    ыгана
    -0.51
    сумка
    -0.48
    Примечания
    -0.46
    haviour
    -0.46
    sä
    -0.46
    gående
    -0.46
     nélk
    -0.45
    ervi
    -0.44
    ilina
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.64
     Athenians
    0.54
    LEncoder
    0.54
    Бахар
    0.53
     Estadual
    0.52
    GenerationType
    0.52
    SequentialGroup
    0.52
     distanciation
    0.51
     combineReducers
    0.51
    providedIn
    0.50
    Activations Density 9.867%

    No Known Activations