© 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. 14270
    Prev
    Next
    INDEX
    Explanations

    the word "states" related to countries, laws, or physical or chemical states

    oai_token-act-pair · gemini-2.0-flash

    states

    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
     GenerationType
    -1.16
    tvguidetime
    -1.13
     CreateTagHelper
    -1.01
    SPATH
    -1.01
    PreferredItem
    -0.98
    AddTagHelper
    -0.98
    PerformLayout
    -0.96
     Мексичка
    -0.96
    NUMX
    -0.95
    windowFixed
    -0.93
    POSITIVE LOGITS
    ↵↵
    1.08
     
    0.89
    <eos>
    0.79
    ↵
    0.78
    The
    0.72
     The
    0.71
     A
    0.70
     '
    0.68
    ↵↵↵
    0.66
    '
    0.66
    Activations Density 0.663%

    No Known Activations