© 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. 12291
    Prev
    Next
    INDEX
    Explanations

    text about beekeeping

    oai_token-act-pair · gemini-2.0-flash

    essential or significant concepts

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

    positive adjectives

    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
     nakalista
    -1.21
     Exactos
    -0.92
    +#+#
    -0.88
     NSCoder
    -0.83
     Theſe
    -0.82
    AnchorStyles
    -0.81
     Efq
    -0.79
     متعلقه
    -0.79
     itſelf
    -0.78
     الحره
    -0.77
    POSITIVE LOGITS
    Suppose
    0.82
     Suppose
    0.75
     essential
    0.72
     excellent
    0.61
     significant
    0.60
    essential
    0.58
     fantastic
    0.55
     ha
    0.54
     vital
    0.54
     ten
    0.51
    Activations Density 1.052%

    No Known Activations