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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10354
    Prev
    Next
    INDEX
    Explanations

    LaTeX math formulas and symbols

    oai_token-act-pair · gemini-2.0-flash

    Math Equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    #+#
    -1.03
    ]--;
    -0.99
     Roskov
    -0.95
     Мексичка
    -0.94
    ]++;
    -0.89
    ]=$
    -0.87
    ')['
    -0.86
    ++]=
    -0.84
     صوتيه
    -0.84
    "}")
    -0.82
    POSITIVE LOGITS
    mo
    0.59
    text
    0.55
    mi
    0.52
    ce
    0.51
    begin
    0.47
    ga
    0.46
    mb
    0.46
    en
    0.46
    b
    0.45
    al
    0.43
    Activations Density 3.757%

    No Known Activations