© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6127
    Prev
    Next
    INDEX
    Explanations

    the word "even"

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

    the word "even"

    oai_token-act-pair · gemini-2.0-flash

    even

    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
    TestingModule
    -0.60
    ValueGenerated
    -0.53
    ThemeOverlay
    -0.52
    Бахар
    -0.49
     Because
    -0.48
     balle
    -0.47
    uber
    -0.47
    getRuntime
    -0.47
     because
    -0.46
    denn
    -0.46
    POSITIVE LOGITS
     though
    0.73
     THOUGH
    0.67
    though
    0.57
     Administrativna
    0.54
    ksikon
    0.54
     ThemeData
    0.53
    Though
    0.52
    ValueGeneration
    0.51
    CodedInputStream
    0.51
    MethodManager
    0.51
    Activations Density 0.303%

    No Known Activations