© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12204
    Prev
    Next
    INDEX
    Explanations

    strings and numbers within sentences, with a particular affinity for percentages

    oai_token-act-pair · gemini-2.0-flash

    specific compounds or terms related to firearms

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

    weapons

    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
    MigrationBuilder
    -1.04
     CreateTagHelper
    -0.85
    awtextra
    -0.83
     تضيفلها
    -0.82
     resourceCulture
    -0.79
     utafitiHapana
    -0.78
    RepeatedField
    -0.76
    Rhestr
    -0.76
     OFDb
    -0.76
    AndEndTag
    -0.75
    POSITIVE LOGITS
    gne
    0.47
     .
    0.47
    Vig
    0.42
     slu
    0.40
    mk
    0.39
    cc
    0.38
     ane
    0.38
    サイクル
    0.38
     anti
    0.37
     val
    0.37
    Activations Density 2.090%

    No Known Activations