© 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. 3169
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to figures, especially their width

    oai_token-act-pair · gemini-2.0-flash

    \

    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
     Dubuque
    -0.59
     Fertility
    -0.55
     Onyx
    -0.54
    󠁢
    -0.54
     crystallization
    -0.53
     jaundice
    -0.53
     Holliday
    -0.53
     Prerequisite
    -0.53
     Sunt
    -0.52
     LoginComponent
    -0.51
    POSITIVE LOGITS
    IndentedString
    0.83
    principalTable
    0.59
    hdashline
    0.57
    oredCriteria
    0.57
    Begriffsklä
    0.53
    the
    0.52
     the
    0.52
    deelte
    0.51
    GEBURTSDATUM
    0.51
    Abitanti
    0.50
    Activations Density 1.052%

    No Known Activations