© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12415
    Prev
    Next
    INDEX
    Explanations

    possessive words or phrases, along with dialogue context

    oai_token-act-pair · gemini-2.0-flash

    mentions of "words" or related terms

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

    words

    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
    ThroughAttribute
    -0.67
    PerformLayout
    -0.52
     politiker
    -0.50
    titleMargin
    -0.49
    Personensuche
    -0.46
    MLLoader
    -0.45
    ָׁ
    -0.45
    )<\
    -0.44
    をつけて
    -0.43
    _),
    -0.43
    POSITIVE LOGITS
     words
    1.18
     statement
    0.91
    words
    0.91
     WORDS
    0.89
     Words
    0.87
    Words
    0.86
     sentence
    0.83
     woorden
    0.79
     слов
    0.78
     palabras
    0.76
    Activations Density 1.843%

    No Known Activations