© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9783
    Prev
    Next
    INDEX
    Explanations

    hex color codes preceded by a '#'

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    g
    -0.78
    H
    -0.76
    G
    -0.73
    w
    -0.72
    j
    -0.72
    r
    -0.71
    M
    -0.70
    X
    -0.70
    W
    -0.68
    V
    -0.68
    POSITIVE LOGITS
     Monfieur
    0.64
     houſe
    0.59
    ViewFeatures
    0.58
     poffe
    0.57
     cauſe
    0.55
     himſelf
    0.54
    daad
    0.54
     chofe
    0.54
    CEED
    0.52
    pośred
    0.52
    Activations Density 1.719%

    No Known Activations