© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15025
    Prev
    Next
    INDEX
    Explanations

    conversational phrases indicating surprise, shock, or strong opinion

    oai_token-act-pair · gemini-2.0-flash

    UI-related programming terms

    np_token-act-pair-logits · gpt-4o-mini

    random text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    bootstrapcdn
    -0.72
    principalColumn
    -0.67
    awtextra
    -0.59
     Référence
    -0.56
     Drapeau
    -0.55
    Newswire
    -0.53
    usercontent
    -0.51
    AutoScale
    -0.51
     تضيفلها
    -0.51
     MainAxisSize
    -0.50
    POSITIVE LOGITS
    WebControls
    0.54
    💼
    0.54
     jenner
    0.49
     Grünen
    0.47
    SafeMath
    0.47
    Gambas
    0.47
    GREES
    0.45
    eqnarray
    0.45
     AppCompatTheme
    0.44
    UIControlState
    0.44
    Activations Density 1.237%

    No Known Activations