© 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. 12910
    Prev
    Next
    INDEX
    Explanations

    words related to legal or privacy agreements in a non-English language, as well as words ending in "ity"

    oai_token-act-pair · gemini-2.0-flash

    words related to privacy

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

    words ending in "ity"

    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
    Trama
    -0.60
     nonatomic
    -0.57
    aneous
    -0.50
    böz
    -0.48
    Theory
    -0.48
    sı
    -0.47
     gynnwys
    -0.46
     sauvage
    -0.45
    (!__
    -0.45
    GenerationType
    -0.45
    POSITIVE LOGITS
    ity
    1.41
    ITY
    1.23
    ities
    1.11
    idade
    1.05
     ity
    1.04
    ties
    1.01
    itys
    0.99
    ty
    0.97
    lty
    0.94
    idad
    0.93
    Activations Density 0.138%

    No Known Activations