© 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. 3484
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and phrases related to experiences and meals

    oai_token-act-pair · gemini-2.0-flash

    Restaurants/meals

    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
    #+#
    -0.88
    levance
    -0.59
     '\\;'
    -0.56
    LabelTagHelper
    -0.55
    AFFIRMED
    -0.54
     run
    -0.53
     immor
    -0.52
    Parcelize
    -0.51
     ModelExpression
    -0.51
    RSpec
    -0.51
    POSITIVE LOGITS
    اخته
    0.51
     Gerais
    0.50
    principalColumn
    0.49
    AndroidJUnit
    0.47
    AccessException
    0.46
    Batis
    0.46
     ticks
    0.44
     وتسجيلات
    0.44
     noten
    0.43
    .*")]
    0.43
    Activations Density 4.686%

    No Known Activations