© 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. 6023
    Prev
    Next
    INDEX
    Explanations

    German sentences containing many verbs and modal verbs.

    oai_token-act-pair · 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
     prieten
    -0.64
     câte
    -0.63
     Majefty
    -0.62
     pleaſure
    -0.62
     Verhält
    -0.60
     Abgerufen
    -0.60
     amitié
    -0.58
     ziua
    -0.58
     Geruch
    -0.58
     reaſon
    -0.57
    POSITIVE LOGITS
    enderror
    0.57
    endphp
    0.56
     &___
    0.55
     fieldNum
    0.54
    TagMode
    0.54
    RegressionTest
    0.53
     referenties
    0.52
    LookAnd
    0.51
     postIndex
    0.50
     lenker
    0.47
    Activations Density 0.246%

    No Known Activations