© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11435
    Prev
    Next
    INDEX
    Explanations

    named Instagram accounts, the word Instagram, celebrities and real estate

    oai_token-act-pair · gemini-2.0-flash

    account

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     posts
    -1.19
     Posts
    -1.10
     posting
    -1.04
     Posting
    -1.01
    posts
    -0.97
    Posts
    -0.94
    Posting
    -0.93
    posting
    -0.91
     POSTS
    -0.90
     postings
    -0.87
    POSITIVE LOGITS
     accounts
    0.88
     account
    0.81
    account
    0.66
    accounts
    0.62
    ACCOUNT
    0.60
     Accounts
    0.57
     comptes
    0.54
     cuentas
    0.52
     Account
    0.51
     accounted
    0.51
    Activations Density 1.372%

    No Known Activations