© 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. 9253
    Prev
    Next
    INDEX
    Explanations

    a lot of common words without clear topical connection and some words or phrases regarding decisions, time, opinions.

    oai_token-act-pair · gemini-2.0-flash

    code-related terms

    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
     lots
    -2.86
    Lots
    -2.72
     Lots
    -2.67
     lot
    -2.61
    lots
    -2.56
    Lot
    -2.33
    lot
    -2.25
     LOTS
    -2.23
     Lot
    -2.23
     LOT
    -2.16
    POSITIVE LOGITS
    igil
    0.64
    InjectAttribute
    0.58
    ällor
    0.54
    InstrumentedTest
    0.54
    SuppressLint
    0.54
     onCancelled
    0.53
    zins
    0.53
    త్ర
    0.52
    فحة
    0.52
    ActionResult
    0.51
    Activations Density 5.367%

    No Known Activations