© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5677
    Prev
    Next
    INDEX
    Explanations

    the word "reached" along with related words like 'reached', 'passes', 'yards',' English' and numbers

    oai_token-act-pair · gemini-2.0-flash

    reached

    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
    xFFFFFFFF
    -0.79
    /−
    -0.76
    xffffffff
    -0.75
    NOPQRST
    -0.66
     "..\..\
    -0.66
    ngths
    -0.64
     ब्रेकडाउन
    -0.64
    cussions
    -0.64
    uesday
    -0.63
    andoah
    -0.63
    POSITIVE LOGITS
    <bos>
    1.35
     enfans
    0.94
     avoient
    0.90
     plufieurs
    0.89
     feroit
    0.85
     mourut
    0.83
     auroit
    0.82
     étoient
    0.81
     ainfi
    0.81
     pitié
    0.78
    Activations Density 1.152%

    No Known Activations