© 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. 15085
    Prev
    Next
    INDEX
    Explanations

    numbers related to bits and bytes

    oai_token-act-pair · gemini-2.0-flash

    bits and data

    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
     bit
    -3.34
    bit
    -2.97
     Bit
    -2.89
    Bit
    -2.88
     BIT
    -2.59
    BIT
    -2.47
    bits
    -2.34
     bits
    -2.31
     Bits
    -2.27
    Bits
    -2.19
    POSITIVE LOGITS
    bewerken
    0.57
    XmlRootElement
    0.54
    StructEnd
    0.52
    ronpa
    0.51
     ExecuteAsync
    0.51
    Tembelea
    0.50
     calendriers
    0.50
    perry
    0.49
    createForm
    0.48
    builtins
    0.48
    Activations Density 3.596%

    No Known Activations