© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14240
    Prev
    Next
    INDEX
    Explanations

    the word "welcome", and sometimes personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    welcome

    np_max-act · gemini-2.0-flash

    welcome

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     تضيفلها
    -0.90
    InputBorder
    -0.87
    ReusableCell
    -0.86
     Chwiliwch
    -0.83
    AxisAlignment
    -0.83
    CloseOperation
    -0.82
    AndEndTag
    -0.81
    antMatchers
    -0.81
     NSCoder
    -0.81
    Datuak
    -0.79
    POSITIVE LOGITS
    <bos>
    2.22
    '
    0.89
    ↵↵
    0.84
    ’
    0.76
    ↵
    0.73
    <strong>
    0.63
    i
    0.59
    The
    0.59
    <h2>
    0.58
    1
    0.58
    Activations Density 2.907%

    No Known Activations