© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8935
    Prev
    Next
    INDEX
    Explanations

    the pronouns "I", "you", "he", "we", and "they" in close proximity to auxiliary verbs and some other words

    oai_token-act-pair · gemini-2.0-flash

    the word 'once' and variations

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

    actions of people

    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
    bootstrapcdn
    -0.90
    MessageOf
    -0.82
    حوالہ
    -0.77
    Autoritní
    -0.75
    ніципа
    -0.74
    PhysRevD
    -0.74
    DockStyle
    -0.69
    expandindo
    -0.68
    tanleria
    -0.65
     betweenstory
    -0.65
    POSITIVE LOGITS
     once
    0.61
    ActionEvent
    0.57
    ttemberg
    0.51
     Rel
    0.47
    Once
    0.46
     στιγ
    0.46
     Once
    0.46
    setupUi
    0.44
    once
    0.43
    ANEOUS
    0.42
    Activations Density 0.634%

    No Known Activations