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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2732
    Prev
    Next
    INDEX
    Explanations

    mentions of proportions, ratios, probabilities or scientific measurements

    oai_token-act-pair · gemini-2.0-flash

    most

    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
     Likely
    -1.20
     likely
    -1.20
    likely
    -1.18
    Likely
    -1.13
     likelihood
    -0.93
    probable
    -0.90
     probable
    -0.89
     waarschijnlijk
    -0.83
    likelihood
    -0.81
     Probable
    -0.79
    POSITIVE LOGITS
     most
    2.59
    most
    2.27
    Most
    2.11
     Most
    1.98
     MOST
    1.74
    MOST
    1.59
     moſt
    1.48
     moft
    1.41
     meest
    1.16
     paling
    0.80
    Activations Density 7.420%

    No Known Activations