© 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. 10486
    Prev
    Next
    INDEX
    Explanations

    positive and comparative adjectives with associated helping verbs and conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    adjectives describing durability

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

    durable

    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
     дописавши
    -0.64
    SourceChecksum
    -0.61
    Дереккөздер
    -0.58
     $\}$
    -0.54
    matchCondition
    -0.52
     صوتيه
    -0.52
    Хьажоргаш
    -0.51
    Personendaten
    -0.51
     \\
    -0.50
    contentLoaded
    -0.49
    POSITIVE LOGITS
     durable
    0.85
     sturdy
    0.76
     Durable
    0.69
    rungsseite
    0.68
    Durable
    0.63
    durable
    0.63
     compact
    0.62
     résistant
    0.61
     Sturdy
    0.61
     resilient
    0.60
    Activations Density 1.159%

    No Known Activations