© 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. 7088
    Prev
    Next
    INDEX
    Explanations

    descriptions of art, crafts, and possibly other decorative items, including the use of adjectives like 'enameled', 'stained', and certain colors.

    oai_token-act-pair · gemini-2.0-flash

    fabrics and designs

    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
     betweenstory
    -0.74
    peutic
    -0.71
    InjectAttribute
    -0.70
    IsMutable
    -0.64
     GetEnumerator
    -0.55
    ographia
    -0.52
    IndentedString
    -0.52
     Metropolitana
    -0.52
    éroport
    -0.51
    opardy
    -0.51
    POSITIVE LOGITS
     الحره
    0.76
    StoryboardSegue
    0.60
     محفوظة
    0.53
    клопе
    0.51
    BeginContext
    0.50
    enumi
    0.49
    MigrationBuilder
    0.47
    地说道
    0.45
    Datuak
    0.45
    appliquer
    0.45
    Activations Density 5.981%

    No Known Activations