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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13551
    Prev
    Next
    INDEX
    Explanations

    various formatting and markup conventions, especially colons, numbering, and references to figures and tables

    oai_token-act-pair · gemini-2.0-flash

    colon punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Baillargeon
    -0.47
    out
    -0.44
    by
    -0.43
    nonatomic
    -0.43
    no
    -0.42
    giveness
    -0.41
     parce
    -0.40
     according
    -0.39
     her
    -0.38
    age
    -0.38
    POSITIVE LOGITS
     تضيفلها
    0.96
     gynhyrchwyd
    0.90
     ModelExpression
    0.90
    bootstrapcdn
    0.87
     يتيمه
    0.84
    TestingModule
    0.82
    TypedDataSet
    0.81
    pushFollow
    0.75
     CreateTagHelper
    0.75
    MLLoader
    0.74
    Activations Density 1.426%

    No Known Activations