© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10301
    Prev
    Next
    INDEX
    Explanations

    the word "hard" used as a prefix

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "hard"

    np_token-act-pair-logits · gpt-4o-mini

    hard

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    évaluateur
    -0.85
    AccessorTable
    -0.79
    AndEndTag
    -0.77
    ьаж
    -0.75
     تضيفلها
    -0.73
    fromnode
    -0.72
     EconPapers
    -0.71
    RenderAtEndOf
    -0.65
    AnchorStyles
    -0.63
    Kilder
    -0.60
    POSITIVE LOGITS
    away
    0.50
    setBold
    0.47
    HttpPut
    0.47
     drives
    0.47
    wired
    0.45
    dima
    0.44
     ware
    0.43
    cup
    0.43
    drives
    0.43
    hed
    0.42
    Activations Density 0.744%

    No Known Activations