© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4496
    Prev
    Next
    INDEX
    Explanations

    mentions of studies, trials, data, methods, and criteria related to medical or psychological conditions

    oai_token-act-pair · gemini-2.0-flash

    academic texts

    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
     néz
    -0.93
     împre
    -0.87
     kysy
    -0.82
     löytyy
    -0.81
     băr
    -0.81
     sähkö
    -0.80
     deschis
    -0.80
     vastaan
    -0.79
     maș
    -0.79
     picioare
    -0.79
    POSITIVE LOGITS
     &
    0.67
     ail
    0.63
     lts
    0.62
     ench
    0.62
     ete
    0.59
     lhe
    0.59
     thc
    0.59
     CanadaChoose
    0.58
    It
    0.58
     It
    0.58
    Activations Density 33.534%

    No Known Activations