© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11255
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     חיצוניים
    -0.52
     d
    -0.44
    失
    -0.41
    semibold
    -0.40
     gib
    -0.40
     continúas
    -0.40
    ceis
    -0.40
     Ely
    -0.39
     r
    -0.38
    php
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.78
    jsonwebtoken
    0.67
     AssemblyVersion
    0.63
     fieldNum
    0.63
    mergeFrom
    0.63
     MainAxisSize
    0.62
    ValueStyle
    0.57
     للاسماء
    0.57
    },[
    0.57
     trattano
    0.57
    Activations Density 3.725%

    No Known Activations