© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 202
    Prev
    Next
    INDEX
    Explanations

    the number one followed by other digits, probably as part of a date or identifier

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CommonModule
    -0.61
    uteen
    -0.56
     pleaſure
    -0.55
    ensement
    -0.54
     houſe
    -0.54
     الاطلاع
    -0.52
    rungsseite
    -0.52
    losis
    -0.51
     riser
    -0.51
     glycine
    -0.51
    POSITIVE LOGITS
    9
    1.13
    8
    1.06
    7
    0.83
     Eighty
    0.63
     девя
    0.60
     eighty
    0.57
    6
    0.57
     nine
    0.56
     nueve
    0.54
     يتيمه
    0.54
    Activations Density 2.744%

    No Known Activations