© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6902
    Prev
    Next
    INDEX
    Explanations

    words related to professions and familial relationships

    oai_token-act-pair · gemini-2.0-flash

    words ending in 'ly' or 'friendliness'

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

    ending in "ly"

    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
    AddTagHelper
    -0.51
    andria
    -0.46
    čiai
    -0.46
     AssemblyCompany
    -0.43
     Olímpicos
    -0.42
    hidupan
    -0.42
    ioneers
    -0.42
    fini
    -0.40
    cích
    -0.40
    تقاوى
    -0.40
    POSITIVE LOGITS
    ly
    1.40
    LY
    1.02
    liness
    0.95
    liest
    0.88
    انه
    0.87
    ish
    0.85
    lier
    0.84
    like
    0.83
    lijke
    0.79
    lys
    0.76
    Activations Density 1.562%

    No Known Activations