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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5917
    Prev
    Next
    INDEX
    Explanations

    Dutch words related to research and organizations

    oai_token-act-pair · gemini-2.0-flash

    miscellaneous data

    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
    ConstraintMaker
    -0.56
    LookAnd
    -0.56
    sizeCache
    -0.51
     transférez
    -0.50
    esez
    -0.49
    webElementXpaths
    -0.49
     noastre
    -0.47
    слова
    -0.46
    Biographie
    -0.46
    jąc
    -0.46
    POSITIVE LOGITS
    bleven
    0.62
    DoubleQuotes
    0.57
    djangoproject
    0.54
     Siria
    0.52
     Sec
    0.51
     Ejec
    0.51
    UnknownFieldSet
    0.50
    WithMany
    0.50
     gesteld
    0.49
    väg
    0.48
    Activations Density 0.201%

    No Known Activations