© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1389
    Prev
    Next
    INDEX
    Explanations

    Javascript code snippets including test assertions

    oai_token-act-pair · gemini-2.0-flash

    Code testing assertions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PerformLayout
    -0.59
    DoubleQuotes
    -0.54
    AddTagHelper
    -0.53
    RG
    -0.52
     saites
    -0.49
    Gön
    -0.48
    featureID
    -0.47
    urtstag
    -0.47
    ptt
    -0.46
    ourced
    -0.46
    POSITIVE LOGITS
    beforeEach
    0.67
    NotBe
    0.66
    execSQL
    0.66
    assertThat
    0.65
    assertThrows
    0.63
    assertNot
    0.62
    teardown
    0.59
    assertSame
    0.59
    assertEqual
    0.57
    assertIs
    0.57
    Activations Density 9.109%

    No Known Activations