© 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. 1262
    Prev
    Next
    INDEX
    Explanations

    the word "sand" and words commonly found near it

    oai_token-act-pair · gemini-2.0-flash

    Detects sand

    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
     sand
    -2.22
     SAND
    -2.20
     Sand
    -2.19
    Sand
    -2.11
    SAND
    -1.98
     sands
    -1.91
    sand
    -1.86
     sandy
    -1.77
     Sands
    -1.69
    Sandbox
    -1.49
    POSITIVE LOGITS
    évaluateur
    0.55
     Capit
    0.55
     VizieR
    0.52
    ValueStyle
    0.50
    setupUi
    0.49
    ogre
    0.48
    rungsseite
    0.48
     OPC
    0.47
     محفوظة
    0.47
    verket
    0.45
    Activations Density 1.295%

    No Known Activations