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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with sport trades and rumors

    oai_token-act-pair · gemini-2.0-flash

    terms related to trading or transactions

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

    News and reports

    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
    انيف
    -0.50
     aspi
    -0.46
     luces
    -0.42
     Volkes
    -0.42
     FBref
    -0.42
    ionine
    -0.40
     wyp
    -0.40
     lights
    -0.40
    siella
    -0.40
    ngOnDestroy
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.80
     shock
    0.66
     initComponents
    0.64
    ClientSize
    0.61
    ificantly
    0.60
    ualaikum
    0.59
    Sklici
    0.59
     shocks
    0.58
    shock
    0.58
    tonode
    0.57
    Activations Density 2.425%

    No Known Activations