© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8304
    Prev
    Next
    INDEX
    Explanations

    the word "stored" and words related to it.

    oai_token-act-pair · gemini-2.0-flash

    stored

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    wußt
    -0.96
     Efq
    -0.93
    stdc
    -0.92
    ^(@)
    -0.91
    $$
    -0.86
    */;
    -0.85
     themſelves
    -0.84
     Eſ
    -0.84
     ―――――
    -0.84
    ')")
    -0.83
    POSITIVE LOGITS
    n
    0.63
     a
    0.63
    ↵↵
    0.56
    m
    0.56
    a
    0.56
    <eos>
    0.54
    M
    0.54
     
    0.52
    r
    0.52
    f
    0.51
    Activations Density 2.160%

    No Known Activations