© 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. 817
    Prev
    Next
    INDEX
    Explanations

    references to time periods and familial or societal structures.

    oai_token-act-pair · gemini-2.0-flash

    size

    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
     يتيمه
    -0.73
     Yarn
    -0.73
     Boat
    -0.67
     Poem
    -0.66
     Papers
    -0.66
     Songs
    -0.66
     Books
    -0.65
     Boats
    -0.63
     Recipe
    -0.63
     Theatre
    -0.62
    POSITIVE LOGITS
     Large
    0.99
     Low
    0.96
     Permanent
    0.95
     Regular
    0.93
     Full
    0.92
     Massive
    0.92
     High
    0.91
     Small
    0.90
    Normal
    0.90
     Normal
    0.90
    Activations Density 57.202%

    No Known Activations