© 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. 4270
    Prev
    Next
    INDEX
    Explanations

    grammatical verb phrases utilizing "be" as an auxiliary verb

    oai_token-act-pair · gemini-2.0-flash

    real

    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
    getClassName
    -0.49
    ांकि
    -0.46
     arah
    -0.46
    uda
    -0.45
    pædia
    -0.45
    anku
    -0.43
     propOrder
    -0.43
    رم
    -0.42
    tabular
    -0.42
    enderror
    -0.42
    POSITIVE LOGITS
     real
    3.39
    real
    2.86
    Real
    2.59
     Real
    2.53
    REAL
    2.27
     REAL
    2.22
     reales
    2.03
     réel
    1.93
     reale
    1.84
     réelle
    1.78
    Activations Density 7.180%

    No Known Activations