© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8557
    Prev
    Next
    INDEX
    Explanations

    the word "without" and words related to giving gifts

    oai_token-act-pair · gemini-2.0-flash

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     without
    -2.13
    Without
    -1.97
     Without
    -1.95
    without
    -1.88
     WITHOUT
    -1.63
    <bos>
    -1.59
     без
    -1.48
     zonder
    -1.45
     tanpa
    -1.45
    WITHOUT
    -1.41
    POSITIVE LOGITS
    tvguidetime
    0.80
     [*]
    0.69
    bootstrapcdn
    0.66
     FontWeight
    0.66
    URLException
    0.64
    interopRequire
    0.63
    lorette
    0.62
    teenth
    0.60
    WaitGroup
    0.59
    InstanceState
    0.59
    Activations Density 0.541%

    No Known Activations