© 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. 580
    Prev
    Next
    INDEX
    Explanations

    code containing hexadecimal and acronyms and underscores

    oai_token-act-pair · gemini-2.0-flash

    Code and errors

    np_max-act-logits · gemini-2.0-flash

    ALL-CAPS abbreviations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     ProtoMessage
    -0.56
    able
    -0.55
     okuyayım
    -0.53
    typeorm
    -0.46
    KURZBESCHREIBUNG
    -0.45
    ValueStyle
    -0.45
     فريبيس
    -0.45
    bcryptjs
    -0.45
    րան
    -0.45
    repor
    -0.45
    POSITIVE LOGITS
    ign
    0.84
    ite
    0.81
    igned
    0.80
    ig
    0.76
    ed
    0.74
    im
    0.73
    ies
    0.71
    tore
    0.69
    ive
    0.69
    ell
    0.69
    Activations Density 4.957%

    No Known Activations