© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5086
    Prev
    Next
    INDEX
    Explanations

    phrases about personal responsibility and stating one's identity

    oai_token-act-pair · gemini-2.0-flash

    Legal/Relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    AndroidJUnit
    -0.89
     propOrder
    -0.78
     AssemblyTitle
    -0.63
     otomatig
    -0.61
     scattata
    -0.60
    rungsseite
    -0.60
     ThemeData
    -0.59
     مشين
    -0.59
    +#+#
    -0.59
    IUrlHelper
    -0.58
    POSITIVE LOGITS
    الإنجليزية
    0.67
     jezelf
    0.52
    ichord
    0.50
     '-':
    0.49
     stessi
    0.49
     yourself
    0.48
     مخطط
    0.48
    uestamente
    0.48
    GrantedAuthority
    0.47
     actores
    0.47
    Activations Density 0.867%

    No Known Activations