© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 652
    Prev
    Next
    INDEX
    Explanations

    a diverse set of things, including single digits, sexual acts, and strings of semicolons, but it's not clear what links them.

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    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
     zare
    -0.50
    ]--;
    -0.42
    eraus
    -0.42
     belf
    -0.42
    lowest
    -0.41
    propri
    -0.40
    بران
    -0.40
    requ
    -0.39
    the
    -0.39
    gated
    -0.39
    POSITIVE LOGITS
     كومونز
    0.96
     propOrder
    0.84
    Viitteet
    0.83
     ProtoMessage
    0.83
    లాలు
    0.73
     EconPapers
    0.72
     AssemblyTitle
    0.71
    帖最后由
    0.70
    setVerticalGroup
    0.69
    — 
    0.68
    Activations Density 18.001%

    No Known Activations