© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5635
    Prev
    Next
    INDEX
    Explanations

    phrases including "best" and some personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    best

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    extAlignment
    -0.56
     piele
    -0.46
    InSection
    -0.44
     cuivre
    -0.44
    tivamente
    -0.42
    mpz
    -0.41
    Explicación
    -0.41
     منها
    -0.40
    נטרנט
    -0.40
    ualmente
    -0.39
    POSITIVE LOGITS
    best
    0.79
     best
    0.74
    httphttps
    0.68
    adaptiveStyles
    0.67
    SharedCtor
    0.65
     besten
    0.64
    AsUp
    0.63
    InitVars
    0.62
    BEST
    0.62
     terbaik
    0.61
    Activations Density 0.410%

    No Known Activations