© 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. 812
    Prev
    Next
    INDEX
    Explanations

    something about multiple topics

    oai_token-act-pair · 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
    sp
    -0.81
    sc
    -0.80
     sp
    -0.79
     sc
    -0.78
     sg
    -0.77
     sn
    -0.77
    sl
    -0.75
     ss
    -0.75
     sm
    -0.75
     sd
    -0.75
    POSITIVE LOGITS
     nakalista
    0.42
    Werdegang
    0.39
     CreateTagHelper
    0.38
    getragen
    0.36
    évaluateur
    0.36
    ایج
    0.36
    Награды
    0.36
     gradova
    0.35
    gdala
    0.35
    lccn
    0.35
    Activations Density 3.474%

    No Known Activations