© 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. 7361
    Prev
    Next
    INDEX
    Explanations

    pairs of words related to anatomical location and scientific measurements

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific text

    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
    TagMode
    -0.58
    principalColumn
    -0.57
    kheim
    -0.56
    ukone
    -0.56
     meanwhile
    -0.52
    GenerationType
    -0.49
    IntoConstraints
    -0.49
    bukkit
    -0.49
    istoitu
    -0.49
    AndEndTag
    -0.48
    POSITIVE LOGITS
     BorderRadius
    0.72
     handker
    0.57
     vectorstock
    0.57
     cister
    0.56
     tongs
    0.55
    Matéri
    0.54
     trenches
    0.53
     octaves
    0.53
     Shells
    0.53
    homology
    0.52
    Activations Density 8.288%

    No Known Activations