© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 975
    Prev
    Next
    INDEX
    Explanations

    relationships between people or entities.

    oai_token-act-pair · gemini-2.0-flash

    names and legal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Portale
    -0.66
    featureID
    -0.56
    IntoConstraints
    -0.56
     disambiguazione
    -0.54
    таратура
    -0.53
    хьтан
    -0.53
     يتيمه
    -0.53
    parsedMessage
    -0.52
     ujednoznacz
    -0.50
    IsMutable
    -0.50
    POSITIVE LOGITS
    l
    0.77
    w
    0.71
    b
    0.71
    n
    0.69
    0
    0.69
    2
    0.69
     l
    0.69
    p
    0.68
    r
    0.68
    t
    0.68
    Activations Density 3.678%

    No Known Activations