© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11859
    Prev
    Next
    INDEX
    Explanations

    words and phrases in a sentence that indicate a suggestion or requirement

    oai_token-act-pair · gemini-2.0-flash

    Instructions/Requests

    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
    енча
    -0.56
    UTERS
    -0.51
     bio
    -0.51
     سياس
    -0.49
    matchCondition
    -0.48
     Biological
    -0.48
     biological
    -0.47
     Streit
    -0.47
     못
    -0.47
     open
    -0.47
    POSITIVE LOGITS
     lenker
    0.74
    migrationBuilder
    0.60
    CppMethod
    0.59
    ngOnDestroy
    0.57
     FixedUpdate
    0.53
    didSet
    0.52
    JvmStatic
    0.52
    ngOn
    0.52
    XtraReports
    0.52
    addCriterion
    0.52
    Activations Density 8.134%

    No Known Activations