© 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. 6821
    Prev
    Next
    INDEX
    Explanations

    uses of the word "is" combined with surrounding adverbs and adjectives and some political terms

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    tonsoft
    -0.68
     nahilalakip
    -0.59
    DeleteBehavior
    -0.59
    nationality
    -0.57
    GeoNames
    -0.57
    BagConstraints
    -0.56
    Skocz
    -0.56
    EndProject
    -0.54
    InputTagHelper
    -0.53
     makeStyles
    -0.53
    POSITIVE LOGITS
     Engle
    0.53
     pinulongan
    0.53
     Paglinawan
    0.51
    PostInfinity
    0.50
     Infórmanos
    0.49
    mjs
    0.49
    TypedValue
    0.47
    Dung
    0.47
    ğe
    0.47
     魔
    0.47
    Activations Density 2.860%

    No Known Activations