© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12579
    Prev
    Next
    INDEX
    Explanations

    descriptive words used in marketing of cars or beauty products

    oai_token-act-pair · gemini-2.0-flash

    abstract qualities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    feels
    -0.61
    looks
    -0.56
    Feels
    -0.54
    tvguidetime
    -0.54
     feels
    -0.52
     looks
    -0.50
    Looks
    -0.48
     Looks
    -0.47
     LOOKS
    -0.47
    stücke
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.90
    CppMethod
    0.73
     Мексичка
    0.71
    PageRoute
    0.70
    iconductor
    0.69
     '{@
    0.69
    ExtendWith
    0.65
     насељу
    0.65
    LEncoder
    0.64
     linkovi
    0.63
    Activations Density 6.384%

    No Known Activations