© 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. 202
    Prev
    Next
    INDEX
    Explanations

    the token "Cor"

    oai_token-act-pair · gemini-2.0-flash

    Cor

    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
     validamos
    -0.58
    енча
    -0.55
    InjectAttribute
    -0.53
    calientes
    -0.52
     nargin
    -0.51
    seamnă
    -0.51
    GEBURTSDATUM
    -0.48
     hObject
    -0.48
     cherchés
    -0.47
     appelez
    -0.47
    POSITIVE LOGITS
    iolis
    0.59
    rona
    0.57
     Audiodateien
    0.56
    adone
    0.53
     TType
    0.53
    digans
    0.51
     surla
    0.51
    rugated
    0.51
    bina
    0.50
    redor
    0.50
    Activations Density 5.220%

    No Known Activations